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 2281–2290 of 15113 papers

TitleStatusHype
Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model—0
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning—0
FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models—0
Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation—0
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning—0
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation—0
Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study—0
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning—0
2048: Reinforcement Learning in a Delayed Reward Environment—0
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across DomainsCode0
Show:102550
← PrevPage 229 of 1512Next →

Benchmark Results

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