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 3311–3320 of 15113 papers

TitleStatusHype
Improving the generalizability and robustness of large-scale traffic signal control—0
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space—0
A Modular Test Bed for Reinforcement Learning Incorporation into Industrial Applications—0
Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations—0
Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction—0
Hyperparameters in Reinforcement Learning and How To Tune Them—0
Deep Q-Learning versus Proximal Policy Optimization: Performance Comparison in a Material Sorting Task—0
An Architecture for Deploying Reinforcement Learning in Industrial Environments—0
Thought Cloning: Learning to Think while Acting by Imitating Human ThinkingCode2
Heterogeneous Knowledge for Augmented Modular Reinforcement Learning—0
Show:102550
← PrevPage 332 of 1512Next →

Benchmark Results

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