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 2791–2800 of 15113 papers

TitleStatusHype
TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion—0
The Crucial Role of Problem Formulation in Real-World Reinforcement Learning—0
Synthesizing world models for bilevel planning—0
Reasoning Beyond Limits: Advances and Open Problems for LLMs—0
Offline Reinforcement Learning with Discrete Diffusion Skills—0
Learning Adaptive Dexterous Grasping from Single Demonstrations—0
Harmonia: A Multi-Agent Reinforcement Learning Approach to Data Placement and Migration in Hybrid Storage Systems—0
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking—0
Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer LearningCode0
Mining-Gym: A Configurable RL Benchmarking Environment for Truck Dispatch SchedulingCode0
Show:102550
← PrevPage 280 of 1512Next →

Benchmark Results

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