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 3451–3460 of 15113 papers

TitleStatusHype
Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning—0
VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers—0
Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare—0
Efficient Reinforcement Learning with Large Language Model Priors—0
Masked Generative Priors Improve World Models Sequence Modelling Capabilities—0
Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching—0
Offline Hierarchical Reinforcement Learning via Inverse Optimization—0
Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement LearningCode0
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning—0
MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning—0
Show:102550
← PrevPage 346 of 1512Next →

Benchmark Results

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