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 21–30 of 15113 papers

TitleStatusHype
The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs—0
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning—0
Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model—0
Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation—0
Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study—0
GTA1: GUI Test-time Scaling AgentCode2
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation—0
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMsCode2
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning—0
Show:102550
← PrevPage 3 of 1512Next →

Benchmark Results

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