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 1711–1720 of 15113 papers

TitleStatusHype
Model-Based Transfer Learning for Contextual Reinforcement LearningCode1
Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs—0
Listwise Reward Estimation for Offline Preference-based Reinforcement LearningCode1
Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary ObjectivesCode0
PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning—0
Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes—0
RELIEF: Reinforcement Learning Empowered Graph Feature Prompt TuningCode1
CADRL: Category-aware Dual-agent Reinforcement Learning for Explainable Recommendations over Knowledge Graphs—0
Integrating Controllable Motion Skills from Demonstrations—0
Model-free optimal controller for discrete-time Markovian jump linear systems: A Q-learning approach—0
Show:102550
← PrevPage 172 of 1512Next →

Benchmark Results

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