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 931–940 of 15113 papers

TitleStatusHype
Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters—0
A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards—0
Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning—0
A Survey of In-Context Reinforcement Learning—0
Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol—0
Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning—0
Active Advantage-Aligned Online Reinforcement Learning with Offline DataCode0
Towards a Formal Theory of the Need for Competence via Computational Intrinsic Motivation—0
Optimal Actuator Attacks on Autonomous Vehicles Using Reinforcement Learning—0
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning—0
Show:102550
← PrevPage 94 of 1512Next →

Benchmark Results

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