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 1811–1820 of 15113 papers

TitleStatusHype
Communicative Reinforcement Learning Agents for Landmark Detection in Brain ImagesCode1
SuperSuit: Simple Microwrappers for Reinforcement Learning EnvironmentsCode1
Safe Reinforcement Learning in Constrained Markov Decision ProcessesCode1
Cautious Adaptation For Reinforcement Learning in Safety-Critical SettingsCode1
Sample-efficient Cross-Entropy Method for Real-time PlanningCode1
OR-Gym: A Reinforcement Learning Library for Operations Research ProblemsCode1
Offline Meta-Reinforcement Learning with Advantage WeightingCode1
TriFinger: An Open-Source Robot for Learning DexterityCode1
SafePILCO: a software tool for safe and data-efficient policy synthesisCode1
The Emergence of Adversarial Communication in Multi-Agent Reinforcement LearningCode1
Show:102550
← PrevPage 182 of 1512Next →

Benchmark Results

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