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 2071–2080 of 15113 papers

TitleStatusHype
PoPS: Policy Pruning and Shrinking for Deep Reinforcement LearningCode1
GridMask Data AugmentationCode1
POPCORN: Partially Observed Prediction COnstrained ReiNforcement LearningCode1
Population-Guided Parallel Policy Search for Reinforcement LearningCode1
Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation ErrorsCode1
Reinforcement Learning via Fenchel-Rockafellar DualityCode1
Deep Reinforcement Learning for Active Human Pose EstimationCode1
Blue River Controls: A toolkit for Reinforcement Learning Control Systems on HardwareCode1
A Boolean Task Algebra for Reinforcement LearningCode1
MushroomRL: Simplifying Reinforcement Learning ResearchCode1
Show:102550
← PrevPage 208 of 1512Next →

Benchmark Results

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