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 2391–2400 of 15113 papers

TitleStatusHype
Learning Dual-arm Object Rearrangement for Cartesian Robots—0
Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark—0
Reinforcement learning-assisted quantum architecture search for variational quantum algorithms—0
AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning—0
Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement LearningCode1
Deep Hedging with Market Impact—0
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning—0
Reflect-RL: Two-Player Online RL Fine-Tuning for LMsCode1
Antifragile Perimeter Control: Anticipating and Gaining from Disruptions with Reinforcement Learning—0
XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning TechniquesCode1
Show:102550
← PrevPage 240 of 1512Next →

Benchmark Results

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