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 911–920 of 15113 papers

TitleStatusHype
DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous DrivingCode1
Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification AlgorithmsCode1
BIMRL: Brain Inspired Meta Reinforcement LearningCode1
Language Control Diffusion: Efficiently Scaling through Space, Time, and TasksCode1
Provable Safe Reinforcement Learning with Binary FeedbackCode1
Low-Rank Modular Reinforcement Learning via Muscle SynergyCode1
ERL-Re^2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy RepresentationCode1
Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real DataCode1
Teal: Learning-Accelerated Optimization of WAN Traffic EngineeringCode1
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement LearningCode1
Show:102550
← PrevPage 92 of 1512Next →

Benchmark Results

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