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 1531–1540 of 15113 papers

TitleStatusHype
Agent-Controller Representations: Principled Offline RL with Rich Exogenous InformationCode1
A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity RewardsCode1
Denoised MDPs: Learning World Models Better Than the World ItselfCode1
De novo PROTAC design using graph-based deep generative modelsCode1
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-SecondCode1
Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement LearningCode1
A Deep Reinforced Model for Abstractive SummarizationCode1
Basis for Intentions: Efficient Inverse Reinforcement Learning using Past ExperienceCode1
Model-Based Transfer Learning for Contextual Reinforcement LearningCode1
A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics NetworkCode1
Show:102550
← PrevPage 154 of 1512Next →

Benchmark Results

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