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 1031–1040 of 15113 papers

TitleStatusHype
DROPO: Sim-to-Real Transfer with Offline Domain RandomizationCode1
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM GuardrailsCode1
Dream to Control: Learning Behaviors by Latent ImaginationCode1
Advancing Multimodal Reasoning via Reinforcement Learning with Cold StartCode1
Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous DrivingCode1
Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement LearningCode1
DRL4Route: A Deep Reinforcement Learning Framework for Pick-up and Delivery Route PredictionCode1
Automatic Data Augmentation for Generalization in Reinforcement LearningCode1
Automatic Data Augmentation for Generalization in Deep Reinforcement LearningCode1
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical RepresentationsCode1
Show:102550
← PrevPage 104 of 1512Next →

Benchmark Results

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