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 1611–1620 of 15113 papers

TitleStatusHype
Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code SynthesisCode1
Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement LearningCode1
Continual Model-Based Reinforcement Learning with HypernetworksCode1
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning DatasetsCode1
CURL: Contrastive Unsupervised Representation Learning for Reinforcement LearningCode1
Automating DBSCAN via Deep Reinforcement LearningCode1
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative ExplorationCode1
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector QuantizationCode1
An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement LearningCode1
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement LearningCode1
Show:102550
← PrevPage 162 of 1512Next →

Benchmark Results

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