SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2026–2050 of 15113 papers

TitleStatusHype
Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement LearningCode0
DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing ProblemsCode1
Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation—0
Rethinking Transformers in Solving POMDPsCode1
Biological Neurons Compete with Deep Reinforcement Learning in Sample Efficiency in a Simulated Gameworld—0
Oracle-Efficient Reinforcement Learning for Max Value Ensembles—0
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step OptimizationCode1
Reinforcement Learning for Jump-Diffusions, with Financial Applications—0
Competing for pixels: a self-play algorithm for weakly-supervised segmentationCode0
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement LearningCode0
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning—0
An Evolutionary Framework for Connect-4 as Test-Bed for Comparison of Advanced Minimax, Q-Learning and MCTS—0
Constrained Ensemble Exploration for Unsupervised Skill Discovery—0
Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlCode2
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy OptimizationCode2
Adaptive Q-Network: On-the-fly Target Selection for Deep Reinforcement Learning—0
AIGB: Generative Auto-bidding via Conditional Diffusion Modeling—0
Embedding-Aligned Language Models—0
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning—0
Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine—0
Diffusion Actor-Critic with Entropy RegulatorCode2
Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning—0
Model-free reinforcement learning with noisy actions for automated experimental control in opticsCode0
Human-in-the-loop Reinforcement Learning for Data Quality Monitoring in Particle Physics Experiments—0
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee—0
Show:102550
← PrevPage 82 of 605Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified