Reward Learning

Follow this topic Ask about this topic

Recent momentum

emerging

2 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Reward Learning.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Reward Learning.

35 papers

Latest in Reward Learning

Open your feed →

Bandits with Probing: Optimal Regret and the Limits of Winner Feedback
Sep 14, 2026Yongjie GuanReward Learning
AlphaRJM: Reward-Jump Memory for Stochastic Return-Guided Alpha Discovery
Sep 8, 2026Sayan Dhan, Selvaraju NatarajanReward Learning Soft Actor-Critic
Efficient Exploration Is Enough
Sep 7, 2026Mikel Malagón, Jon Vadillo, Josu Ceberio +2Efficient Exploration Reward Learning
Short-Term Pain for Long-Term Gain: Adaptive Experiment with Post-Commitment Reward Shift
Jul 26, 2026Puping Jiang, Wei TangPlan Regret Reward Learning
Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
Jul 22, 2026Hongju PaeReward Learning Latent Reasoning
Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
Jul 18, 2026Patrick Cooper, Alvaro VelasquezPartially Observable Markov Decision Process Free Energy Principle
Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy Estimators
Jul 18, 2026Alireza Furutanpey, Schahram DustdarReward Learning Intrinsic Motivation
When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal
Jul 11, 2026James E. AllchinReward Learning Latent States
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
Jul 9, 2026Ali Larian, Qian Lin, Chang Zong Wu +1Reward Learning Reward Functions
Best-Arm Identification with Generative Proxy
Jul 8, 2026Tianyi Ma, Hanzhang Qin, Ruihao Zhu +1Reward Learning Heteroskedasticity
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
Jun 19, 2026Marco Pratticò, Pietro Novelli, Massimiliano Pontil +1Reward Learning Safe Reinforcement Learning
Can In-Context Learning Support Intrinsic Curiosity?
Jun 17, 2026Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald +5In-Context Learning Reward Learning
UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
Jun 17, 2026Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang +1Reward Learning Sublinear Regret
Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards
Jun 17, 2026Zirong LiReward Learning Learning-Augmented Algorithms
Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking
Jun 4, 2026Bonan Shen, Youting Wang, Dingyan Shang +1Contextual Reasoning Prompt Injection Detection
FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization
Jun 3, 2026Yihao Wu, He Zhang, Junbo Tan +2Diffusion-Based Vision-Language-Actions Reinforcement Fine-Tuning
A No-Regret Framework for Adaptive Incentive Design
Jun 1, 2026Georgios Vasileiou, Lantian Zhang, Silun ZhangIncentives Optimal Policies
The Representation-Rationalizability Tradeoff in Reward Learning
May 29, 2026Jing Dong, Yaoliang Yu, Pascal PourpartReward Learning Pairwise Preferences
Reward Learning from Best-of- $N$ Preference Data: Targets, Tradeoffs, and Design PrinciplesReward Learning from Best-of-N Preference Data: Targets, Tradeoffs, and Design Principles
May 28, 2026Rattana Pukdee, Maria-Florina Balcan, Pradeep RavikumarBest-Of-N Preference Learning
A Minimal Bifurcation Model of Load Imbalance in a Softmax Mixture-of-Experts Router
May 27, 2026O. M. KiselevMixture-Of-Expert Routing Bifurcation
Exploratory Experience Shapes the Geometry of Predictive Representations
May 27, 2026Kseniia Shilova, Abdelrahman Sharafeldin, Advay Balakrishnan +1Predictive Coding Perception-Action Loop
Finite-Time Regret Analysis of Retry-Aware Bandits
May 20, 2026Bingkui Tong, Junpei Komiyama, Soichiro Nishimori +1Sublinear Regret Regret
Active Context Selection Improves Simple Regret in Contextual Bandits
May 19, 2026Mohammad Shahverdikondori, Jalal Etesami, Negar KiyavashMulti-Objective Bandits Adaptive Sampling
Not all uncertainty is alike: volatility, stochasticity, and exploration
May 19, 2026Payam PirayStochastic Exploration Curiosity-Driven Exploration
When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
May 18, 2026Peiying Zhu, Sidi ChangReward Learning Prices
Delightful Exploration
May 13, 2026Ian OsbandStochastic Exploration Generalized Linear Bandit
Controllability in preference-conditioned multi-objective reinforcement learning
May 11, 2026Pau de las Heras Molins, Beyazit Yalcinkaya, Lasse Peters +2Multi-Objective Reinforcement Learning Reward Learning
Equilibrium Residuals Expose Three Regimes of Matrix-Game Strategic Reasoning in Language Models
May 11, 2026Wenhua Nie, Binhan Luo, Zijie Meng +2Imperfect-Information Games Equilibrium
Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State
May 7, 2026Peiying Zhu, Sidi ChangPrices Matching Markets
RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences
May 3, 2026Yangyang Zhou, Yi-Chen LiReward Learning
A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
Apr 27, 2026Ying-Tu Chen, Wei Hung, Bing-Shu Wu +2Multi-Objective Reinforcement Learning Reward Learning
A single algorithm for both restless and rested rotting bandits
Apr 23, 2026Julien Seznec, Pierre Ménard, Alessandro Lazaric +1Bandits Reward Learning
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Apr 20, 2026Vin Bhaskara, Haicheng WangPointwise Forecasting Losses Reward Learning
Best of both worlds: Stochastic & adversarial best-arm identification
Apr 16, 2026Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon +2Generalized Linear Bandit Bandits
Learning Peer Influence Probabilities with Linear Contextual Bandits
Oct 21, 2025Ahmed Sayeed Faruk, Mohammad Shahverdikondori, Elena ZhelevaLightweight Tabular Contextual Bandit Efficient Influence Function

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

Bandits with Probing: Optimal Regret and the Limits of Winner Feedback

Yongjie Guan

A learner probes at most

k

n

arms each round, receives the maximum of their rewards in

[0,1]

, and competes with the best fixed arm. When does the probing advantage pay for learning? We determine two minimax laws. Under independent stochastic rewards with winner feedback (the maximum and a winning label), or on arbitrary fixed sequences given a single signed contrast between block maxima, the minimax regret has order

Φ_{n,k}(T)=\min\{\frac{n-k}{n}T,\frac{n-k}{k}\}

2\le k<n

. Under winner feedback, both arbitrary joint i.i.d. rewards and fixed sequences have minimax regret of order

R_{n,k}(T)=\frac{n-k}{n}\min\{T,\frac{n+T}{k},\sqrt{\frac{nT}{k}}\}

. Both laws have universal constants and anytime upper bounds. The first reduces regret to a pure coverage cost: same-round contrasts absorb the stability cost, and independence permits exact resampling whose gains fund sample advancement. The second adds a learning cost that becomes comparable to coverage at horizon

n

; beyond

nk

, numerical maxima improve over labels alone. The lower bound allows every adaptive action size.

Reward Learning

Open paper Ask about it PDF