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 1951–1960 of 15113 papers

TitleStatusHype
Combining Reinforcement Learning with Model Predictive Control for On-Ramp MergingCode1
CommonPower: A Framework for Safe Data-Driven Smart Grid ControlCode1
Compositional Reinforcement Learning from Logical SpecificationsCode1
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language ModelsCode1
Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement LearningCode1
Self-Activating Neural Ensembles for Continual Reinforcement LearningCode1
Self-Driving Network and Service Coordination Using Deep Reinforcement LearningCode1
Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification AlgorithmsCode1
Self-Supervised Discovering of Interpretable Features for Reinforcement LearningCode1
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement LearningCode1
Show:102550
← PrevPage 196 of 1512Next →

Benchmark Results

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