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 276–300 of 15113 papers

TitleStatusHype
Learning to Fly in SecondsCode2
JaxMARL: Multi-Agent RL Environments and Algorithms in JAXCode2
Diffusion Models for Reinforcement Learning: A SurveyCode2
TD-MPC2: Scalable, Robust World Models for Continuous ControlCode2
Distributional Soft Actor-Critic with Three RefinementsCode2
RLLTE: Long-Term Evolution Project of Reinforcement LearningCode2
A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement LearningCode2
Text2Reward: Reward Shaping with Language Models for Reinforcement LearningCode2
Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal ModelsCode2
Benchmarking Potential Based Rewards for Learning Humanoid LocomotionCode2
When Do Transformers Shine in RL? Decoupling Memory from Credit AssignmentCode2
InterCode: Standardizing and Benchmarking Interactive Coding with Execution FeedbackCode2
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXCode2
Datasets and Benchmarks for Offline Safe Reinforcement LearningCode2
QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust ControlCode2
RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous ControlCode2
Thought Cloning: Learning to Think while Acting by Imitating Human ThinkingCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex ManipulationCode2
DiffMimic: Efficient Motion Mimicking with Differentiable PhysicsCode2
Language Models can Solve Computer TasksCode2
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement LearningCode2
POPGym: Benchmarking Partially Observable Reinforcement LearningCode2
Reward Design with Language ModelsCode2
Assessment of Reinforcement Learning for Macro PlacementCode2
Show:102550
← PrevPage 12 of 605Next →

Benchmark Results

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