Reinforcement Learning

Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.

Papers

November 2, 2024

Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shaping
Chanjuan Liu, Jinmiao Cong, Bingcai Chen, Yaochu Jin, Enqiang Zhu
Reinforcement Learning New Framework Multi Agent Reinforcement Learning Multi Agent Reward Function Part Whole Hierarchy Reward Shaping
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
Ziqing Fan, Shengchao Hu, Yuhang Zhou, Li Shen, Ya Zhang, Yanfeng Wang, Dacheng Tao
Reinforcement Learning Decision Transformer Action Free Offline Diverse Policy Task Similarity
Rule Based Rewards for Language Model Safety
Tong Mu, Alec Helyar, Johannes Heidecke, Joshua Achiam, Andrea Vallone, Ian Kivlichan, Molly Lin, Alex Beutel, John Schulman, Lilian Weng
Language Model Reinforcement Learning Reward Report Simple RULE AI Feedback Safety Fine Tuning Preference Model

November 1, 2024

Effective ML Model Versioning in Edge Networks
Fin Gentzen, Mounir Bensalem, Admela Jukan
Reinforcement Learning Machine Learning Machine Learning Model Edge Network Model Versioning
Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Region
Tobias Egle, Yashuai Yan, Dongheui Lee, Christian Ott
Reinforcement Learning Region Specific Bipedal Robot Step Size Feasible Trajectory Push Recovery Footstep Induced Signal Step Count Stepping Control
Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmas
Brian Mintz, Feng Fu
Reinforcement Learning Multi Agent Reinforcement Learning Q Learning Evolutionary Game Theory Social Dilemma Public Good Game
Beyond the Boundaries of Proximal Policy Optimization
Charlie B. Tan, Edan Toledo, Benjamin Ellis, Jakob N. Foerster, Ferenc Huszár
Reinforcement Learning Proximal Policy Optimization Gradient Based Document Boundary Gradient Ascent
Self-Evolved Reward Learning for LLMs
Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao, Zeqi Lin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Large Language Model Language Model Reinforcement Learning Reward Model Self Feedback
Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback
Song Yu, Xiaofei Xu, Fangfei Xu, Li Li
Large Language Model Language Model Reinforcement Learning Supervised Fine Tuning AI Feedback Traditional Chinese Medicine
StepCountJITAI: simulation environment for RL with application to physical activity adaptive intervention
Karine Karine, Benjamin M. Marlin
Reinforcement Learning Application Proficiency Simulation Environment Adaptive Policy Adaptive Intervention Step Count
A Review of Reinforcement Learning in Financial Applications
Yahui Bai, Yuhe Gao, Runzhe Wan, Sheng Zhang, Rui Song
Reinforcement Learning Financial Application Markov Decision Process Narrative Review Multi Agent RL

October 31, 2024

From Easy to Hard: Tackling Quantum Problems with Learned Gadgets For Real Hardware
Akash Kundu, Leopoldo Sarra
Reinforcement Learning Quantum Circuit Quantum Algorithm Quantum Processor Hardware Environment
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
Mujin Cheon, Jay H. Lee, Dong-Yeun Koh, Calvin Tsay
Reinforcement Learning Bayesian Optimization High Dimensional Bayesian Optimization Large Scale Hyperparameter Optimization Lookahead Heuristic
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
Jiajun Xi, Yinong He, Jianing Yang, Yinpei Dai, Joyce Chai
Reinforcement Learning Human Language Diversity Awareness Embodied AI Implicit Knowledge Learning Agent Language Feedback Task Learning
Zonal RL-RRT: Integrated RL-RRT Path Planning with Collision Probability and Zone Connectivity
AmirMohammad Tahmasbi, MohammadSaleh Faghfoorian, Saeed Khodaygan, Aniket Bera
Reinforcement Learning Path Planning Collision Probability
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
Kai Yan, Alexander G. Schwing, Yu-Xiong Wang
Reinforcement Learning Offline Reinforcement Learning Decision Transformer Online Fine Tuning Deeper ViT S 54
Maximum Entropy Hindsight Experience Replay
Douglas C. Crowder, Matthew L. Trappett, Darrien M. McKenzie, Frances S. Chance
Reinforcement Learning Proximal Policy Optimization Policy Reinforcement Learning Hindsight Experience Replay
Deterministic Exploration via Stationary Bellman Error Maximization
Sebastian Griesbach, Carlo D'Eramo
Reinforcement Learning Environment Exploration Intrinsic Reward Exploration Policy Bellman Error Random Exploration
Towards Reliable Alignment: Uncertainty-aware RLHF
Debangshu Banerjee, Aditya Gopalan
Language Model Reinforcement Learning Reward Model Reinforcement Learning From Human Feedback
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Weichao Zhou, Wenchao Li
Reinforcement Learning Adversarial Attack Related Task Alignment Problem Inverse Reinforcement Learning Task Alignment Database Alignment

Reinforcement Learning

Papers

Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shaping

Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

Rule Based Rewards for Language Model Safety

Effective ML Model Versioning in Edge Networks

Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Region

Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmas

Beyond the Boundaries of Proximal Policy Optimization

Self-Evolved Reward Learning for LLMs

Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback

StepCountJITAI: simulation environment for RL with application to physical activity adaptive intervention

A Review of Reinforcement Learning in Financial Applications

From Easy to Hard: Tackling Quantum Problems with Learned Gadgets For Real Hardware

EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Zonal RL-RRT: Integrated RL-RRT Path Planning with Collision Probability and Zone Connectivity

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

Maximum Entropy Hindsight Experience Replay

Deterministic Exploration via Stationary Bellman Error Maximization

Towards Reliable Alignment: Uncertainty-aware RLHF

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment