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 2451–2460 of 15113 papers

TitleStatusHype
Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits—0
Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy—0
A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs—0
Learning Diverse Policies with Soft Self-Generated Guidance—0
Code as Reward: Empowering Reinforcement Learning with VLMs—0
SEABO: A Simple Search-Based Method for Offline Imitation LearningCode1
Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning AgentsCode0
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model FeedbackCode2
Averaging n-step Returns Reduces Variance in Reinforcement Learning—0
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement LearningCode1
Show:102550
← PrevPage 246 of 1512Next →

Benchmark Results

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