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 1791–1800 of 15113 papers

TitleStatusHype
Text Generation by Learning from DemonstrationsCode1
Meta-AAD: Active Anomaly Detection with Deep Reinforcement LearningCode1
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly DataCode1
Deep Actor-Critic Learning for Distributed Power Control in Wireless Mobile NetworksCode1
Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware DetectionCode1
Reinforcement Learning for Optimal Primary Frequency Control: A Lyapunov ApproachCode1
DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous ControlCode1
Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement LearningCode1
Phasic Policy GradientCode1
Deep Active Inference for Partially Observable MDPsCode1
Show:102550
← PrevPage 180 of 1512Next →

Benchmark Results

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