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 641–650 of 15113 papers

TitleStatusHype
Enhanced Penalty-based Bidirectional Reinforcement Learning Algorithms—0
Dexterous Manipulation through Imitation Learning: A Survey—0
Learning Dual-Arm Coordination for Grasping Large Flat Objects—0
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation SchemeCode2
Adapting World Models with Latent-State Dynamics Residuals—0
Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language ModelsCode0
Multi-SWE-bench: A Multilingual Benchmark for Issue ResolvingCode3
MAD: A Magnitude And Direction Policy Parametrization for Stability Constrained Reinforcement LearningCode0
Inference-Time Scaling for Generalist Reward Modeling—0
Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research—0
Show:102550
← PrevPage 65 of 1512Next →

Benchmark Results

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