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 1161–1170 of 15113 papers

TitleStatusHype
Equivariant Action Sampling for Reinforcement Learning and Planning—0
Using machine learning to inform harvest control rule design in complex fishery settingsCode0
MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning—0
RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM EnhancementCode1
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization—0
Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation—0
Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents—0
Are Expressive Models Truly Necessary for Offline RL?Code1
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement LearningCode1
Entropy-Regularized Process Reward ModelCode1
Show:102550
← PrevPage 117 of 1512Next →

Benchmark Results

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