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 1581–1590 of 15113 papers

TitleStatusHype
Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction ReportCode1
Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online PlanningCode1
On the Importance of Hyperparameter Optimization for Model-based Reinforcement LearningCode1
Modular Object-Oriented Games: A Task Framework for Reinforcement Learning, Psychology, and NeuroscienceCode1
A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement LearningCode1
Information Directed Reward Learning for Reinforcement LearningCode1
Memory-based Deep Reinforcement Learning for POMDPsCode1
Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and modelCode1
Reinforcement Learning with Prototypical RepresentationsCode1
Exploiting Multimodal Reinforcement Learning for Simultaneous Machine TranslationCode1
Show:102550
← PrevPage 159 of 1512Next →

Benchmark Results

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