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 3291–3300 of 15113 papers

TitleStatusHype
Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RLCode1
Timing Process Interventions with Causal Inference and Reinforcement Learning—0
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataCode1
CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments—0
Value Functions are Control Barrier Functions: Verification of Safe Policies using Control TheoryCode1
Mildly Constrained Evaluation Policy for Offline Reinforcement LearningCode0
Model-Based Reinforcement Learning with Multi-Task Offline PretrainingCode0
Boosting Offline Reinforcement Learning with Action Preference Query—0
PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation—0
RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous ControlCode2
Show:102550
← PrevPage 330 of 1512Next →

Benchmark Results

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