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
Accelerating Goal-Conditioned RL Algorithms and ResearchCode3
Reinforcement Learning Meets Visual OdometryCode3
Simplifying Deep Temporal Difference LearningCode3
Is Value Learning Really the Main Bottleneck in Offline RL?Code3
CarDreamer: Open-Source Learning Platform for World Model based Autonomous DrivingCode3
ACEGEN: Reinforcement learning of generative chemical agents for drug discoveryCode3
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RLCode3
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement LearningCode3
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement LearningCode3
Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid AlgorithmsCode3
Generating Synergistic Formulaic Alpha Collections via Reinforcement LearningCode3
OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning ResearchCode3
Learning Bipedal Walking for Humanoids with Current FeedbackCode3
EvoTorch: Scalable Evolutionary Computation in PythonCode3
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement LearningCode3
imitation: Clean Imitation Learning ImplementationsCode3
Adversarial Cheap TalkCode3
MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning LibraryCode3
Discovered Policy OptimisationCode3
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and PlanningCode3
Learning Bipedal Walking On Planned Footsteps For Humanoid RobotsCode3
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online VideosCode3
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning AlgorithmsCode3
On the Use and Misuse of Absorbing States in Multi-agent Reinforcement LearningCode3
Tianshou: a Highly Modularized Deep Reinforcement Learning LibraryCode3
Show:102550
← PrevPage 5 of 605Next →

Benchmark Results

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