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 3521–3530 of 15113 papers

TitleStatusHype
Accelerating exploration and representation learning with offline pre-training—0
Language Models can Solve Computer TasksCode2
Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions—0
When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning—0
On the Analysis of Computational Delays in Reinforcement Learning-based Rate Adaptation Algorithms—0
Learning in Factored Domains with Information-Constrained Visual Representations—0
MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from ObservationsCode0
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement LearningCode2
Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks—0
Does Sparsity Help in Learning Misspecified Linear Bandits?—0
Show:102550
← PrevPage 353 of 1512Next →

Benchmark Results

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