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 1921–1930 of 15113 papers

TitleStatusHype
Conservative Q-Learning for Offline Reinforcement LearningCode1
Randomized Entity-wise Factorization for Multi-Agent Reinforcement LearningCode1
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply ChainsCode1
Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample ComplexityCode1
Deployment-Efficient Reinforcement Learning via Model-Based Offline OptimizationCode1
Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement LearningCode1
Single-step deep reinforcement learning for open-loop control of laminar and turbulent flowsCode1
Interferobot: aligning an optical interferometer by a reinforcement learning agentCode1
Combining Reinforcement Learning and Constraint Programming for Combinatorial OptimizationCode1
PlanGAN: Model-based Planning With Sparse Rewards and Multiple GoalsCode1
Show:102550
← PrevPage 193 of 1512Next →

Benchmark Results

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