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 2541–2550 of 15113 papers

TitleStatusHype
Blackout Mitigation via Physics-guided RLCode0
Deployable Reinforcement Learning with Variable Control RateCode0
DeLF: Designing Learning Environments with Foundation ModelsCode0
Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation—0
UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender SystemsCode1
Bridging State and History Representations: Understanding Self-Predictive RLCode1
Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation—0
Learning from Sparse Offline Datasets via Conservative Density EstimationCode0
PRewrite: Prompt Rewriting with Reinforcement Learning—0
CycLight: learning traffic signal cooperation with a cycle-level strategy—0
Show:102550
← PrevPage 255 of 1512Next →

Benchmark Results

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