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 4071–4080 of 15113 papers

TitleStatusHype
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and DetectionCode0
Dual Ensemble Kalman Filter for Stochastic Optimal Control—0
Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis—0
Adaptable Recovery Behaviors in Robotics: A Behavior Trees and Motion Generators(BTMG) Approach for Failure Management—0
Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning—0
FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback—0
Compositional Conservatism: A Transductive Approach in Offline Reinforcement LearningCode0
Transform then Explore: a Simple and Effective Technique for Exploratory Combinatorial Optimization with Reinforcement Learning—0
Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand ManipulationCode0
Enhancing IoT Intelligence: A Transformer-based Reinforcement Learning Methodology—0
Show:102550
← PrevPage 408 of 1512Next →

Benchmark Results

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