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 101–125 of 15113 papers

TitleStatusHype
OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning ResearchCode3
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRsCode3
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlCode3
MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning LibraryCode3
Learning Bipedal Walking On Planned Footsteps For Humanoid RobotsCode3
Learning to Reason under Off-Policy GuidanceCode3
CarDreamer: Open-Source Learning Platform for World Model based Autonomous DrivingCode3
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning AlgorithmsCode3
Deep Reinforcement LearningCode3
On the Use and Misuse of Absorbing States in Multi-agent Reinforcement LearningCode3
Is Value Learning Really the Main Bottleneck in Offline RL?Code3
imitation: Clean Imitation Learning ImplementationsCode3
General-Reasoner: Advancing LLM Reasoning Across All DomainsCode3
Flow Q-LearningCode3
Generating Synergistic Formulaic Alpha Collections via Reinforcement LearningCode3
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement LearningCode3
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise RewardCode3
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and ReasoningCode3
Fine-Tuning Language Models from Human PreferencesCode3
ACEGEN: Reinforcement learning of generative chemical agents for drug discoveryCode3
EvoTorch: Scalable Evolutionary Computation in PythonCode3
A Clean Slate for Offline Reinforcement LearningCode3
ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement LearningCode3
Test-Time Training Scaling Laws for Chemical Exploration in Drug DesignCode3
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative FinanceCode3
Show:102550
← PrevPage 5 of 605Next →

Benchmark Results

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