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 1901–1925 of 15113 papers

TitleStatusHype
rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching TasksCode1
RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning WorkloadsCode1
RLx2: Training a Sparse Deep Reinforcement Learning Model from ScratchCode1
R-MADDPG for Partially Observable Environments and Limited CommunicationCode1
Combining Deep Reinforcement Learning and Search for Imperfect-Information GamesCode1
RobocupGym: A challenging continuous control benchmark in RobocupCode1
Robot Navigation in Constrained Pedestrian Environments using Reinforcement LearningCode1
Combinatorial Optimization with Policy Adaptation using Latent Space SearchCode1
Robust Adversarial Reinforcement LearningCode1
A Workflow for Offline Model-Free Robotic Reinforcement LearningCode1
Learning to combine primitive skills: A step towards versatile robotic manipulationCode1
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic CurriculumCode1
BabyAI 1.1Code1
Zero-Shot Compositional Policy Learning via Language GroundingCode1
Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryCode1
Robust Reinforcement Learning using Adversarial PopulationsCode1
A Modular Framework for Reinforcement Learning Optimal ExecutionCode1
Robust Risk-Aware Reinforcement LearningCode1
Combining Reinforcement Learning with Model Predictive Control for On-Ramp MergingCode1
Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley ValuesCode1
rSoccer: A Framework for Studying Reinforcement Learning in Small and Very Small Size Robot SoccerCode1
Addressing Function Approximation Error in Actor-Critic MethodsCode1
SABLAS: Learning Safe Control for Black-box Dynamical SystemsCode1
safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in RoboticsCode1
Collision Probability Distribution Estimation via Temporal Difference LearningCode1
Show:102550
← PrevPage 77 of 605Next →

Benchmark Results

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