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 3721–3730 of 15113 papers

TitleStatusHype
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods—0
Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control—0
Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach—0
A Review of Nine Physics Engines for Reinforcement Learning Research—0
PID Accelerated Temporal Difference Algorithms—0
Token-Mol 1.0: Tokenized drug design with large language model—0
Structural Design Through Reinforcement LearningCode0
Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing—0
Continuous Control with Coarse-to-fine Reinforcement Learning—0
Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning—0
Show:102550
← PrevPage 373 of 1512Next →

Benchmark Results

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