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 8076–8100 of 15113 papers

TitleStatusHype
Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR—0
Near-Optimal Adversarial Reinforcement Learning with Switching Costs—0
Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation—0
Near-Optimal Differentially Private Reinforcement Learning—0
Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments—0
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction—0
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism—0
Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities—0
Near-optimal Policy Identification in Active Reinforcement Learning—0
Near Optimal Policy Optimization via REPS—0
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning—0
Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs—0
Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control—0
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning—0
Near-optimal Regret Bounds for Reinforcement Learning—0
Near-optimal Regret Bounds for Stochastic Shortest Path—0
Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback—0
Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback—0
Near-optimal Reinforcement Learning in Factored MDPs—0
Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes—0
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting—0
Near-Optimal Reinforcement Learning with Self-Play—0
Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver—0
Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model—0
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning—0
Show:102550
← PrevPage 324 of 605Next →

Benchmark Results

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