RL Benchmarks

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 62

Oct 4, 2026cs.AI

Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning

We introduce Factoriax, a GPU-accelerated factory-building simulator written in JAX. In Factoriax, an agent must collect resources, build machines using those resources, and then automate the collection and crafting process by arranging machines on the map to build production pipelines. This paper discusses the structure of the Factoriax simulator and an initial benchmark called Easy Rocket in which an agent is tasked with building a resource-intensive machine called the Rocket in a limited number of game ticks to escape the planet. We also publish results from a number of PPO-based training runs on Easy Rocket. Factoriax is built to be fast. A 1-billion-step PPO training run, equivalent to 500,000 episodes, runs on Easy Rocket in about 8 minutes on a single NVIDIA A100. A standard laptop GPU can complete the same run in about 84 minutes. Our trained PPO agent learns to gather resources, craft machines from those resources, and place them on the map through a curriculum reward directly tied to a manually designed set of achievements. After training, the agent does not place machines in a functional spatial configuration, failing to fully complete the benchmark, and leaving the challenge open for future attempts.

Mickey Beurskens, Tristan Tomilin, Thiago D. Simão

Eindhoven University of Technology

RL Benchmarks Reinforcement Learning

Sep 30, 2026cs.LG

ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning

In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next decision. Memory architectures and benchmarks for RL mostly test retention, the ability to keep information unchanged until it is needed. We formalize two further requirements. Rewriting sets the decision-relevant content to a value independent of the old one, and experience fusion transforms the old content by a rule that a later observation specifies. For tasks built from such updates, we count the memory states that a solution needs, and several baselines reach their lowest success rates on compositions that need more states. We introduce ALER (Adaptive Learnable Experience Rewriting), an agent that pairs an LSTM with a slot memory. An independently addressed Gumbel-Softmax write that concentrates its weight on one slot overwrites that slot, and a learned gate fuses the retrieved content with the recurrent state before the policy and value heads. We also introduce Rune-Mazes, three environments in which rune observations invert, cancel, reset, or repeat updates of a hidden cue under vector and pixel observations. Against seven baselines, ALER reaches a success rate of at least

0.82

in all sixteen Endless T-Maze configurations and at least

0.99

on all five Rune T-Maze compositions, and it has the highest mean success rate on four-branch Rune Multi-Corridor with an Invert rune. On pixel-based Rune MiniGrid Memory, it has a higher mean success rate than PPO-LSTM in eight of ten configurations. Project page: https://quartz-admirer.github.io/ALER-Adaptive-Learnable-Experience-Rewriting/.

Oleg Shchendrigin, Egor Cherepanov, Aleksandr I. Panov +1

Innopolis University, Innopolis, Russia · MIRIAI, Moscow, Russia · Cognitive AI Systems Lab, Moscow, Russia

RL Benchmarks Reinforcement Learning Partially Observable RL

Sep 30, 2026cs.CL

CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL

During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking. Despite its risks to training efficiency and safety, monitoring and mitigating reward hacking during training remain challenging, which is limited by a lack of testbeds that reproduce hacking and reliably identify it. We introduce CATCH, a controllable testbed for studying reward hacking in coding RL. CATCH deliberately exposes environmental loopholes and provides execution-based gold labels by comparing success under a vulnerable evaluator with task correctness under an independent audit. It also can control the model's initial hacking tendency through supervised fine-tuning data mixtures and the difficulty of earning rewards through reward designing, enabling systematic comparisons of hacking dynamics and interventions. Experiments show that CATCH can produce diverse RL training trajectories with clear reward hacking, and analyses demonstrate that both initial models and reward difficulties shape the emergence of reward hacking. We further evaluate the effectiveness of different reward hacking detection and mitigation methods. A key finding is that a chain-of-thought monitor initially suppresses hacking, but this protection erodes as the policy model learn to mislead the monitor with code comments. This highlights the need to evaluate hacking mitigations throughout training with CATCH. The source code and resources are publicly released at https://github.com/THUAIS-Lab/CATCH.

Shouli Wang, Yanfeng Jia, Zhihao Ou +6

Tsinghua University · Beihang University · Southern University of Science and Technology +2

RL Benchmarks RL for Code Generation Reward Hacking Reinforcement Learning with Verifiable Rewards Reward Design for RL

Sep 29, 2026cs.LG

Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL

Training agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides a precise and structured formalism for specifying instructions to agents, and has been successfully adopted for training generalist multi-task policies. However, differences in implementations, task distributions, and evaluation protocols make existing methods difficult to compare, while high computational costs limit the scale and statistical reliability of experiments. We introduce Jaxolotl, a unified high-performance benchmark suite for multi-task LTL-RL to address these concerns. Jaxolotl provides a modular, end-to-end JAX implementation of six representative algorithms and four environments, together with newly curated task suites and a standardised, statistically robust evaluation protocol. By precompiling symbolic task representations into static arrays, Jaxolotl enables fully JIT-compiled training and evaluation, achieving end-to-end speedups of up to

220\times

and supporting controlled comparisons at substantially greater experimental scale. We use this framework to systematically evaluate existing approaches, revealing complementary strengths and limitations: general methods capable of non-myopic reasoning struggle as the number of propositions grows, while methods with stronger scaling rely on environment-specific assumptions and suffer from myopia.

Mathias Jackermeier, Jacques Cloete, Alessandro Abate

Department of Computer Science, University of Oxford · Oxford Robotics Institute, University of Oxford

RL Benchmarks Reinforcement Learning Multi-Task RL

Sep 29, 2026cs.MA

PowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets

Power markets are a natural testbed for multi-agent reinforcement learning (MARL), where multiple self-interested participants repeatedly submit bids. A market-clearing mechanism then determines dispatch and prices subject to power grid constraints and market settlement rules. However, existing MARL environments typically focus on a single market setting, implement simplified clearing mechanisms, or rely on CPU-based optimization solvers that slow large-scale training and limit the systematic study of bidding strategies and market behavior. We introduce PowerMarketJax, a benchmark suite for MARL across five power markets: day-ahead wholesale, real-time balancing, ancillary services, peer-to-peer double auctions, and local flexibility. Each environment implements its own clearing, pricing, and settlement rules while providing a common framework for learning and evaluation. We find that learned bidding behavior depends strongly on the market design: independent learners can miss better strategies when gains require many agents to change together, when more profitable strategies lie beyond a region of lower profit, or when profits disappear as more agents adopt the same strategy. PowerMarketJax implements both market simulation and policy training in JAX, allowing the entire pipeline to run on the GPU with 1,024 X 1,200 parallelisms across both environments and market participants, achieving up to 33X speedup over CPU-based baselines. Our open-source benchmark is available at: https://github.com/powermarketjax/PowerMarketJax.

Zhanhua Pan, Xin Qin, Xiao Liu +3

Nanyang Technological University, Singapore. · Cornell University, USA. · University of Bristol, UK.

RL Benchmarks Multi-Agent Reinforcement Learning

Sep 28, 2026cs.AI

PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning

Power system operation is a safety-critical sequential decision-making problem, making it a natural testbed for reinforcement learning (RL). However, existing RL environments for power systems are often narrow in scope and computationally limited by CPU-based simulation workflows, making large-scale evaluation difficult. We introduce PowerZooJax, a JAX-based benchmark suite for RL in power system operation. It provides five constrained Markov decision process tasks spanning generation, transmission, distribution, distributed energy resources, and data center microgrid. By rewriting power flow, economic dispatch, market clearing, and device dynamics as JAX computation graphs, PowerZooJax keeps the entire training and evaluation loop on the GPU. Experiments show substantial speedups over CPU-based simulations and demonstrate standardized evaluation of policy returns, safety violations, and out-of-distribution stress conditions. Our open-source benchmark is available at: https://github.com/powerzoojax/PowerZooJax.

Zhanhua Pan, Xiao Liu, Zhilong Cao +2

Nanyang Technological University, Singapore. · Cornell University, USA. · University of Bristol, UK.

RL Benchmarks Constrained RL

Sep 28, 2026cs.AI

GlyphBench: A Playground for Language-Model Reinforcement Learning

We introduce GlyphBench, an environment suite for reinforcement learning (RL) post-training of language-model agents, with over 360 tasks spanning diverse games. GlyphBench renders spatial observations as two-dimensional Unicode grids and connects training, evaluation, and trajectory replay through a unified interface designed to support efficient and reproducible research. We use GlyphBench to study how observation interfaces, reasoning effort, and agent harnesses affect performance, and how RL configurations shape learning dynamics. Our results show that glyph observations outperform native text and pixels in our Craftax experiments, with further gains on several BALROG environments. RL on 100 GlyphBench tasks improves Qwen3.5-4B on held-out Reasoning Gym problems, reaching 63.48% accuracy and outperforming the base model, a math-trained baseline, and a code-trained baseline. These experiments provide empirical evidence that reasoning gains from gameplay can yield stronger transfer than math or code. Together, these results highlight GlyphBench's value as a testbed for systematic research on how language-model agents learn, interact, and generalize.

Roger Creus Castanyer, Marc-Alexandre Côté, Matthew James Sargent +3

Mila - Quebec Artificial Intelligence Institute · Université de Montréal · Vmax

RL Benchmarks RL for Language Models RL for Language Model Reasoning RL for LLM Agents

Sep 15, 2026cs.LG

REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff

A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend on underlying environmental reversibility, a property absent in real world manipulation, where events such as pushing objects off tables or spilling granular substances cannot be undone. We introduce REVERSAL-BENCH, a benchmark that controls reversibility via a continuous parameter

ρ\in [0, 1]

and provides a reset oracle, a ground-truth verification mechanism to test state recoverability across eight manipulation settings in five physics engines. Evaluating a broad spectrum of policy architectures, including standard actor-critic algorithms, safe RL, and specialized reset-free frameworks, reveals a sharp reversibility cliff: reset-free agents are consistently absorbed into irrecoverable states as

ρ

increases, whereas episodic agents maintain steady learning. We see this failure mode across autonomous reset-free baselines and constrained RL. Because reset-free agents lack external resets, any transition into an irrecoverable state results in permanent absorption, leaving the agent trapped where further learning halts. We show that this absorption phenomenon persists in full physics simulations under learned manipulation policies. By evaluating against geometrically identical reversible counterparts, we confirm that this breakdown is causally driven by irreversibility rather than obstacle complexity. We release the benchmark suite, a large multi-simulator dataset labeled with recoverability and a reset oracle. We also evaluate a safety shield that intervenes before irreversible failures occur, showing that while recoverability can be predicted accurately, active recovery primarily succeeds only when the agent can physically steer clear of the trap

Riyaaz Shaik, Chandru Venkataraman

Apple

RL Benchmarks Reinforcement Learning Robotic RL Robot Manipulation Benchmarks

Sep 14, 2026cs.AI

Evaluation Metrics for Safe Reinforcement Learning

Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its expected cumulative cost below a specified safety bound. Existing safe RL benchmarks predominantly report whether an algorithm is safe on average, following this expectation-based guarantee. We argue that this convention is insufficient to reliably characterize an algorithm's true safety: it fails to capture how often and how severely the safety bound is violated, whether this holds consistently across tasks and safety bounds, and whether training-time behavior is representative of behavior of the final converged policy. Therefore, we introduce (i) evaluation metrics for safe RL that address each of these concerns and in addition allow for aggregation across tasks and safety bounds. We furthermore define (ii) a safety tier system to systematically categorize and compare algorithms in terms of safety and reliability at both training and for a final policy. Using this framework, we provide (iii) an empirical safety evaluation across multiple safety navigation tasks. Our results show that aggregate metrics, distributional reporting, and task- and safety bound-specific results each reveal information the other metrics cannot. We therefore recommend reporting all three jointly, rather than compressing this information into a single value, as is common practice. We provide SafeRLEval, an open-source evaluation suite to support the reliable characterization of safety in future safe RL research.

Lindsay Spoor, Aske Plaat, Thomas Moerland

Leiden Institute of Advanced Computer Science, Leiden University, Leiden, the Netherlands

RL Benchmarks Constrained RL Safe RL

Sep 14, 2026cs.AI

VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets

Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We introduce VRL-Bench, a harness for fair evaluation of trial-and-error learning under finite trial budgets. Across three models on MiniWoB and WebShop, we evaluate updates from several prominent verbal-memory methods spanning Reflexion and later work: each improves observed success over memory-free retry in some settings but reduces it in others. Replay experiments show that using reflection can reduce success rates, revealing a trade-off between exploiting experience and continued exploration. We propose VEX

^2

, a verbal exploration--exploitation scheduler that uses a language model to jointly select policies and allocate the remaining trial budget. VEX

^2

is the only evaluated update to achieve positive observed success-rate gains over retry in all six settings.

Yu Bai, Yukai Miao, Dawei Wang +8

Zhongguancun Laboratory · Tsinghua University · Network Management Center, China Mobile

RL Benchmarks Reinforcement Learning Exploration-Exploitation Tradeoff RL for LLM Agents

Sep 1, 2026cs.LG

Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control

Reinforcement learning achieves strong traffic signal control performance in simulation, yet policies trained in simulators often fail once deployed in the real world, a failure known as the Sim-to-Real gap. When RL is applied to traffic signal control, this gap arises from several sources: sensing, action execution, traffic dynamics, and the control objective. Their relative impact and the reliability of existing Sim-to-Real mitigation methods remain insufficiently understood, and the field lacks a standard benchmark for systematically measuring the gap and evaluating mitigation methods. We present Sim2Signal, a benchmark that decomposes the Sim-to-Real gap into observation, action, transition, and reward gaps, corresponding to mismatches in the four components of the underlying MDP, and induces each gap in isolation under a shared protocol. We evaluate 18 mitigation methods on 2 base controllers, across 33 gap settings and 10 calibrated networks built from 5 real-world locations. We find that direct transfer consistently degrades performance across all four gap sources, but the severity of the degradation does not predict the effectiveness of mitigation. Instead, mitigation effectiveness depends strongly on the network and gap setting: outside the action gap, a method that helps in one case may fail in another. The most effective methods generally estimate what the gap changes, rather than make the policy insensitive through domain randomization or invariant representations. Our code is available at https://github.com/DaRL-LibSignal/Sim2Signal

Ferdous Al Rafi, Susrik Mukherjee, Latika Liladhar Dekate +6

Arizona State University

RL Benchmarks Sim-to-Real Transfer Traffic Signal Control

Aug 17, 2026cs.AI

Chronocooked: A Benchmark for Interval Timing in Reinforcement Learning Agents

Interval timing is extensively studied as an important aspect of human behaviour. As artificial agents are increasingly designed to function alongside humans, their interval timing abilities also needs to be studied. However, research in this area remains limited and scattered. This paper presents Chronocooked, a reinforcement learning (RL) benchmark environment that enables a systematic study of interval timing abilities in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios involving interval timing tasks drawn from the psychology literature. The tasks and reward functions are designed such that temporal information is unobserved but critical for optimal performance. The environment is intentionally kept simple to enable controlled experiments and support biologically plausible models. Each task is accompanied by evaluation metrics to study different aspects of interval timing in RL agents, namely, task performance, human-like timing and scalability. We report baselines using a non-recurrent architecture (CNN), a recurrent architecture (LSTM), and a biologically inspired recurrent architecture (CTRNN). The baseline model analysis shows that, although RL agents can successfully perform time-dependent tasks, they do not necessarily process and perceive time in the same way as humans. Understanding these differences is important for anticipating their impact on human-robot interactions (HRI).

Amrapali Pednekar, Alvaro Garrido-Perez, Yara Khaluf +1

Department of Information Technology IDLab, Ghent University - imec · Computer Science Department Vrije Universiteit Amsterdam

Aug 10, 2026cs.AI

DSLE: A Learning Environment for Dark Souls Boss Encounters

We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks through a Gymnasium-style interface. DSLE combines real-time combat, high-dimensional visual input, and sparse terminal rewards, with each environment step being a real action executed against the running game. To support controlled comparison, we define DSLE-5, a representative five-boss subset, spanning a melee fight, a spatially constrained arena, an environmental-hazard fight, a multi-target fight, and a fast final-boss fight, that we recommend as the starting suite for agents built on DSLE. On DSLE-5 we evaluate a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. The expert system and the evolutionary baseline each defeat the Asylum Demon, the game's tutorial boss (63% and 43% peak win rates), but none of the five methods defeats the other four DSLE-5 bosses; PPO and DQN show no measurable learning (at most 0.33% win rate on the tutorial boss, 0% elsewhere) within a budget that already costs tens of wall-clock hours per run. A broader study running the evolutionary baseline across all 22 encounters under advantaged all level-50 stats yields wins on only a handful of additional early-game bosses and leaves the rest unwon. The failure cases range from sub-10-second deaths in cramped, multi-target encounters to minute-long stalemates that inflict almost no damage, and we report them through survival time and damage dealt rather than win rate alone.

Derin Gezgin, Jim O'Connor, Tanner Goodwin +1

Autonomous Agent Learning Lab Connecticut College New London, Connecticut, USA

RL Benchmarks Game-Playing Agents

Jul 23, 2026cs.LG

TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning

Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after training. Evaluating such deletion is difficult because a lower membership score can reflect trajectory removal, residual memorization visible to another attack, or policy collapse that destroys useful behavior. We introduce Trajectory-level memOrization and Unlearning in offline RL (TOUR), a benchmark that combines trajectory-level partitioning, matched non-member controls, retraining references, retained-performance anchors, and multi-attack privacy auditing. Across D4RL locomotion experiments and an exploratory AntMaze extension, TOUR shows that common deletion baselines have environment-dependent privacy-utility behavior. Retraining and fine-tuning often provide stronger retained-utility references than uniform GA+Refit, while TrajDeleter remains a useful comparator but is not uniformly stronger under the same audit. Reference-model, threshold, deviation, equivalence, action-error, representation-based, and query-limited attacks further show that a single likelihood-based membership score can overstate deletion quality. In the evaluated settings, conclusions about offline RL unlearning are therefore not stable under single-score auditing. They depend on matched non-member construction, retraining-relative calibration, attack family, retained utility, and explicit scope for diagnostic architecture or component-level evidence.

Chaofan Pan, Lingfei Ren, Xiangyu Jiang +6

1Southwestern University of Finance and Economics · 2Shanxi University

RL Benchmarks Membership Inference Attacks Offline RL Machine Unlearning

Jul 17, 2026cs.LG

Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning

Reinforcement learning (RL) has achieved strong results in control, yet learned policies remain brittle to changes in dynamics, action spaces, observation spaces, or goals, a critical limitation for real-world deployment. Existing benchmarks offer limited diversity and complexity, making it difficult to rigorously study transfer, multi-task learning, and meta-learning in RL. We introduce Building2Building (B2B), a large-scale suite of realistic Heating, Ventilation, and Air Conditioning (HVAC) control environments built on EnergyPlus, a state-of-the-art building simulator. B2B is fully compatible with the Gymnasium interface and features a parametric building generator, enabling the systematic generation of diverse building configurations with heterogeneous observation and action spaces. Based on this suite, we define benchmark tasks targeting key open challenges in RL, including goal adaptation, dynamics adaptation, action-space shifts, and cross-domain transfer. By providing a large-scale, diverse, and physically grounded testbed with standardized evaluation protocols, B2B enables systematic investigation of generalization and transfer in continuous control. Beyond advancing research on generalization in RL, this new benchmark also carries significant societal implications by enabling improved HVAC control at scale, one of the most energy-intensive systems in buildings.

Vincent Taboga, Justin Veilleux, Doseok Jang +2

1Mila - Quebec AI Institute · 2Université de Montréal - Département d’Informatique et de Recherche Opérationnelle

RL Benchmarks Reinforcement Learning Multi-Task RL Heating, Ventilation, and Air Conditioning Control

Jul 14, 2026cs.LG

OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning

Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of out-of-distribution conditions is pivotal to determining when an agent's observations, transitions, or trajectory dynamics deviate from the assumptions underpinning its policy training. Current out-of-distribution (OOD) detection benchmarks typically evaluate image classifiers or static low-dimensional datasets, failing to account for the complex, action-dependent temporal structure inherent in RL trajectories. To address this gap, we present OOD-RL-Bench, a comprehensive and extensible framework designed to evaluate OOD detectors against categories of anomalies injected into RL trajectories. Detectors and anomaly injectors are integrated through shared interfaces and configuration, which allows new scoring methods and perturbation families to be evaluated without modification of the core benchmark loop. We evaluate the utility of the framework using a Deep Q-Network policy within the LunarLander-v3 environment. We assess the performance of each detector across a suite of anomaly types using matched-time AUROC, matched-time AUPRC, matched-time false-positive rate, detection delay, and segmented-onset metrics. Our analysis reveals significant performance variance across anomaly types: observation perturbations and regime switches are identified with high accuracy by several methods, while observation delay and action-conditioned dynamics remain difficult even when post-onset anomaly scores are compared against clean scores from the same timesteps. We make the framework, trained policy checkpoint, and complete results publicly available as a reproducible artefact.

Emil Mittag, Richard Dazeley, Peter Vamplew

Deakin University, Geelong, Victoria, 3220, Australia · Federation University Australia, Ballarat, Victoria, 3350, Australia

RL Benchmarks Online Anomaly Detection OOD Detection

Jul 11, 2026cs.AI

Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems

Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 38% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems.

Rongping Zhou, Omid Tavallaie, Shuaijun Chen +1

School of Computer Science, The University of Sydney, Camperdown NSW 2050, Australia · Department of Engineering Science, University of Oxford, Wellington Square, Oxford OX1 2JD, United Kingdom · Department of Computer Science, The University of Western Australia, 241, 35 Stirling Hwy, Crawley WA 6009

RL Benchmarks Reinforcement Learning Sim-to-Real Transfer

Jul 8, 2026cs.LG

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade. In this paper, we focus on the key ingredients of this research progress and we analyze the canonical evaluation and design paradigms in reinforcement learning. We introduce the theoretical foundations of scaling laws in reinforcement learning and show that the asymptotic performance of reinforcement learning algorithms does not have a monotone relationship between performance rankings and data-regimes. We conduct large-scale experiments and our results demonstrate that a line of reinforcement learning research under the canonical design and evaluation paradigms resulted in incorrect conclusions. Our analysis and results provide a core analysis on scaling, capacity and complexity of deep reinforcement learning.

Ezgi Korkmaz

RL Benchmarks Reinforcement Learning

Jul 7, 2026cs.AI

FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment, benchmark several reinforcement learning algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.

Chase McDonald, Nathan Tsang, Wesley N. Kerr

Como Research · Riot Games

RL Benchmarks Game-Playing Agents Imperfect-Information Games Zero-Sum Games Agent Benchmarks

Jul 2, 2026cs.AI

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym suite, GPT-5.5 achieves the strongest aggregate rank score and top-two performance on all 16 environments. Beyond leaderboard results, EvoPolicyGym also provides trajectory-level diagnostics that distinguish how agents allocate budget, convert feedback into parametric tuning. These analyses show that strong autonomous policy evolution depends not only on isolated task wins, but on discovering task-appropriate mechanisms and refining policies under bounded feedback.

Zhilin Wang, Han Song, Runzhe Zhan +13

University of Science and Technology of China · The Chinese University of Hong Kong · University of Macau +5

RL Benchmarks AI Agent Benchmarks Self-Evolving Agents

Jun 29, 2026cs.LG

RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning

Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbations that can severely degrade performance. Research in adversarial reinforcement learning is often limited by fragmented implementations, inconsistent evaluation protocols, and poor reproducibility. To address these challenges, we present \textbf{RoAd-RL}, an open-source benchmarking framework that provides unified abstractions for policies, attacks, defenses, and robustness metrics, together with reproducible evaluation pipelines and seamless integration with Stable-Baselines3 and Gymnasium. We evaluate DQN, PPO, and SAC agents in LunarLander and Highway-v0 under 192 attack-defense configurations. Results reveal substantial variations in robustness across environments and show that some commonly used defenses can be more detrimental than the attacks they aim to mitigate, while temporal smoothing consistently achieves strong performance. RoAd-RL establishes a standardized benchmark for adversarial reinforcement learning research and is publicly available at https://pypi.org/project/road-rl.

Adithya Mohan, Daniel Kriegl, Torsten Schön

AImotion Bavaria · Technische Hochschule Ingolstadt · Ingolstadt, Germany

RL Benchmarks Reinforcement Learning Adversarial Robustness Robust RL

Jun 26, 2026cs.LG

Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy

One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment settings. When running experiments, however, the goal of achieving high performance in the simulator can mutate into focusing exclusively on solving the simulator. To achieve high scores, researchers may adopt solutions exclusively meant for solving simulators, rather than learning while the agent is deployed outside a simulator. Solving simulators is also worthy of investigation, but it is a fundamentally different RL research question. In this paper, we argue that RL researchers need to distinguish between two use cases of simulators: solving simulators and using simulators as a proxy for learning in deployment. We first discuss how these two use-cases are importantly different, in terms of constraints on how the agent can use the simulator, which algorithms are appropriate, and which evaluation metrics are appropriate. We then highlight several issues and misleading conclusions that can occur by not making the distinction between these two settings clear, supported with examples and simple experiments. This work is a call to the community to begin clearly distinguishing how they are using simulators in their work, hopefully sparking further discussion on which empirical practices work best in each setting.

Matthew Vandergrift, Esraa Elelimy, Martha White

Department of Computing Science, University of Alberta · Alberta Machine Intelligence Institute (Amii) · Canada CIFAR AI Chair

RL Benchmarks Reinforcement Learning Sim-to-Real Transfer

Jun 21, 2026cs.AI

SVGym (SciVerseGym): An Environment for Reinforcement Learning and Bayesian Optimization in Crystal Discovery

Machine-learned interatomic potentials now enable efficient atomistic evaluation for interactive materials discovery, yet closed-loop crystal search methods remain fragmented across bespoke pipelines for editing, relaxation, scoring, constraints, and bookkeeping. We introduce SciVerseGym, a Gymnasium-compatible environment for sequential crystal discovery that frames crystal design as a Markov decision process. Agents observe an atomistic structure, apply chemically meaningful edits, and receive feedback from a configurable evaluator. SciVerseGym supports local and global actions, including elemental substitution, lattice perturbation, atomic displacement, vacancy creation, and atom insertion, along with configurable chemical spaces, structure pools, atomistic and graph-based observations, custom rewards, optional relaxation, and stability or phonon-related diagnostics. Each step applies an edit, evaluates the candidate using a machine-learned interatomic potential or any ASE-compatible calculator, and returns the standard (obs, reward, terminated, truncated, info) tuple. By decoupling agent logic from materials infrastructure, SciVerseGym provides an open, reproducible, and extensible testbed for reinforcement learning, Bayesian optimization, evolutionary search, and language-agent workflows in closed-loop crystal discovery. Code is available at: https://github.com/Bin-Cao/SciVerseGym.

Bin Cao

The Hong Kong University of Science and Technology (Guangzhou), China · Huawei Noah’s Ark Lab, UK

RL Benchmarks Crystal Structure Generation

Jun 19, 2026cs.LG

The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning

Mathematical search problems present a unique challenge for Reinforcement Learning (RL) due to vast search spaces and sparse rewards. In previous works, the Andrews-Curtis (AC) conjecture was established as an illustrative example of such problems. In this work, we identify a critical structural barrier in the AC landscape: a "Two-Hump" distribution, where problem instances are either trivially solvable or effectively impossible, with a scarcity of intermediate "hard-but-solvable" instances required for effective learning. We tackle this challenge through two primary avenues: novel data generation techniques to populate the difficulty gap, and significant algorithmic enhancements including the introduction of supermoves and Transformer-based architectures. We demonstrate substantial performance improvements over previous baselines, and release new comprehensive benchmark datasets including AC-19 (125,192 AC-trivial presentations of varying difficulty with length at most 19) and AC-1M (1,136,154 hard AC-trivial presentations of length at most 30), the first large-scale, publicly available datasets of this kind.

Lucas Fagan, Michele Tarquini, Ali Shehper +6

Department of Mathematics, California Institute of Technology, Pasadena, CA, USA · Institute of Mathematics, University of Zurich, Zurich, Switzerland · Zero Latency Labs +1

RL Benchmarks Reinforcement Learning Sparse-Reward RL

Jun 18, 2026cs.LG

CRAX: Fast Safe Reinforcement Learning Benchmarking

Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing 3D physics-based safety benchmarks remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine, CRAX leverages vectorized operations and hardware acceleration, yielding up to 200x faster training over comparable CPU-based safety benchmarks. The benchmark features eight tasks spanning three difficulty levels and multiple agent morphologies. Evaluating seven popular safe RL methods, we find that none dominates across tasks, and that learning safe policies from pixels remains largely unsolved.

Tristan Tomilin, Mourad Boustani, Mickey Beurskens +2

Eindhoven University of Technology

RL Benchmarks Reinforcement Learning Robot Safety Safe RL

Jun 17, 2026cs.LG

Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning

Offline reinforcement learning (ORL) offers the potential to improve the quality of clinical decision-making using historical electronic health record (EHR) data. Current training and evaluative practices in this field rely heavily on EHR datasets that have been temporally discretised into fixed, regular time intervals. Discretisation creates fictional representations of complex clinical scenarios and compromises the generalisability of retrospective model evaluations. In this paper, we introduce Insulin4RL, a healthcare ORL dataset featuring naturally irregular inputs and actions from real clinical trajectories. Derived from MIMIC-IV, Insulin4RL comprises over 375,000 labelled decisions across 12,209 patients requiring insulin infusion titration in the Intensive Care Unit. The dataset can thus be used for research into ORL model performance under realistic clinical sampling assumptions. We provide a description of the dataset's structure and characteristics, baseline performance metrics using model-free offline reinforcement learning, and a standardised evaluation protocol using fitted Q-evaluation. We conclude with suggested areas for future research that could be addressed using this resource.

Thomas Frost, Steve Harris

Institute of Health Informatics University College London London, United Kingdom

RL Benchmarks Offline RL

Jun 3, 2026cs.RO

MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground Environment

Underground mines present extreme conditions for autonomous robot navigation: GPS is denied, lighting is degraded, and tunnel topology is loop-rich and non-convex. Simulation benchmarks grounded in real production-mine geometry and compatible with GPU-accelerated learning pipelines do not yet exist in the open-source ecosystem. We present MineXplore, an open-source MuJoCo-based navigation benchmark derived from the Leung et al. 2017 Chilean underground copper mine dataset. The environment reconstructs a 104,423 sq.m tunnel network through an six-stage contour-to-MJCF pipeline incorporating octagonal wall cross-sections, LiDAR-sourced jagged wall geometry, three terrain friction zones, a global 5 degree incline, and periodic spot lighting. Geometric fidelity is validated at an Intersection over Union (IoU) of 0.9538 against the source survey map, and surface texture similarity scores 79.4% across six structural dimensions. A single-agent PPO baseline trained via RLlib across five independent random seeds achieves a best rolling coverage of 88.89% (3 of 5 seeds reaching the 90% coverage target), confirming that MineXplore supports stable and reproducible policy learning under realistic underground sensing and topology.

Abhishek S, Badrikanath Praharaj, Sreeram MV

BuildMachineLabs

RL Benchmarks Robot Navigation Robotics RL Exploration

May 31, 2026cs.LG

A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning

Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals. Existing RL formulations and simulated environments, however, are based on discrete-time MDPs with fixed decision intervals. Thus, it remains difficult to evaluate whether RL methods can handle time-interval-dependent disease progression, personalized treatment response, and safety between consecutive measurement points. To address this gap, we introduce MedGym, a benchmark environment for dynamic treatment recommendation. MedGym models longitudinal patient evolution in a continuous-time framework and constructs a configurable medical RL benchmark from clinical data by using Physics-Informed Neural Networks. The resulting benchmark enables direct comparison between discrete-time and continuous-time methods under irregular treatment timing and patient-specific dynamics. Furthermore, MedGym supports evaluation from clinically important perspectives, such as personalization and trajectory-level safety. By providing a standardized and configurable benchmark for continuous-time dynamic treatment, MedGym enables more realistic and informative evaluation of medical RL methods.

Yuepeng Wang, Ken Kawano, Yoshihiko Fujisawa +12

Tokyo University of Agriculture and Technology · Institute of Science Tokyo · National University of Singapore +5

RL Benchmarks Reinforcement Learning Clinical Decision Support Continuous-Time RL Safe RL

May 30, 2026cs.LG

Task diversity produces systematic transfer but inhibits continual reinforcement learning

Continual reinforcement learning (RL) aims to produce agents that never stop adapting to new tasks. A key question is how this interacts with the diversity of tasks an agent experiences. Prior work has shown that training on many diverse tasks leads to agents with strong zero-shot and in-context adaptation. However, this work evaluated agents after they'd stopped learning, i.e. with frozen weights. How task diversity affects an agent's ability to continue learning over a sequence of distribution shifts remains unclear. We introduce Banyan, a GPU-accelerated continual RL domain where one can parametrically control three independent axes that define a task: the map layouts an agent must navigate, the objects it must interact with, and the hierarchical structures of sub-goal dependencies. We find that increasing diversity along each axis induces systematic transfer -- that is, agents begin training on a new task distribution near the performance attained on the previous one, even when the shift changes the structure of the optimal policy. While increasing diversity improves systematic transfer, we find that too much diversity inhibits a learner's ability to continue adapting to new task distributions. As diversity increases, learners plateau in the success rate they achieve on new tasks, yet continue improving on old tasks -- even without further exposure to them. We find this phenomenon manifests across continual learning algorithms, memory architectures, architecture sizes, and in Kinetix -- a physics-based control domain. We release Banyan as a domain for running controlled experiments that study continual RL in the many-tasks regime. Code is available at https://github.com/nhshah15/banyan.

Purab Seth, Neil Shah, Ishaan Sinha +4

Harvard College · University of Washington · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University +1

RL Benchmarks Reinforcement Learning Continual Learning Transfer Learning Generalization in RL Continual RL

May 30, 2026cs.AI

Certificate-Guided Evaluation of Reinforcement Learning Generalization

This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks. Our framework defines a family of inductive reach-avoid tasks, characterized by structural similarities in task dynamics, enabling evaluation of generalization capabilities. We introduce a neural certificate function that validates trajectories generated by RL algorithms by enforcing key conditions, thereby serving as a litmus test for RL generalization. We empirically demonstrate our method's capability in certifying generalization for several state-of-the-art generalizable RL algorithms on challenging continuous environments. Our results show that a lower percentage of certificate function violations correlates with a higher number of test tasks successfully solved, highlighting the effectiveness of our framework in evaluating and distinguishing generalization capabilities of RL algorithms. This work provides a principled approach for benchmarking RL generalization.

Vignesh Subramanian, Đorđe Žikelić, Suguman Bansal

School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA · School of Computing and Information Systems, Singapore Management University, Singapore

RL Benchmarks Reinforcement Learning Generalization in RL