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 2531–2540 of 15113 papers

TitleStatusHype
GRIT: Teaching MLLMs to Think with Images—0
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL—0
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems—0
ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning—0
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning—0
RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning—0
AAPO: Enhance the Reasoning Capabilities of LLMs with Advantage Momentum—0
KIPPO: Koopman-Inspired Proximal Policy Optimization—0
Normalized Cut with Reinforcement Learning in Constrained Action Space—0
Think-J: Learning to Think for Generative LLM-as-a-JudgeCode0
Show:102550
← PrevPage 254 of 1512Next →

Benchmark Results

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