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 831–840 of 15113 papers

TitleStatusHype
Quantitative Resilience Modeling for Autonomous Cyber Defense—0
Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation—0
All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning—0
What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret—0
Active Alignments of Lens Systems with Reinforcement Learning—0
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRsCode3
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model LearningCode2
Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning—0
Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models—0
Minimax Optimal Reinforcement Learning with Quasi-Optimism—0
Show:102550
← PrevPage 84 of 1512Next →

Benchmark Results

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