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 1141–1150 of 15113 papers

TitleStatusHype
Autonomous Reinforcement Learning: Formalism and BenchmarkingCode1
AutoPhoto: Aesthetic Photo Capture using Reinforcement LearningCode1
Efficient Diffusion Policies for Offline Reinforcement LearningCode1
Avalon: A Benchmark for RL Generalization Using Procedurally Generated WorldsCode1
A Deep Reinforcement Learning Approach to First-Order Logic Theorem ProvingCode1
Avalanche RL: a Continual Reinforcement Learning LibraryCode1
A Workflow for Offline Model-Free Robotic Reinforcement LearningCode1
Efficient Reinforcement Learning Through Trajectory GenerationCode1
BabyAI 1.1Code1
FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior RegularizationCode1
Show:102550
← PrevPage 115 of 1512Next →

Benchmark Results

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