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 3351–3360 of 15113 papers

TitleStatusHype
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language UseCode0
A Non-Monolithic Policy Approach of Offline-to-Online Reinforcement LearningCode0
Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play—0
Maximum Entropy Hindsight Experience Replay—0
Self-Driving Car Racing: Application of Deep Reinforcement Learning—0
SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving—0
Offline Behavior DistillationCode0
Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation—0
Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning—0
Stepping Out of the Shadows: Reinforcement Learning in Shadow Mode—0
Show:102550
← PrevPage 336 of 1512Next →

Benchmark Results

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