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 2511–2520 of 15113 papers

TitleStatusHype
Dynamic Sampling that Adapts: Iterative DPO for Self-Aware Mathematical Reasoning—0
PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning ProjectsCode0
Strategically Linked Decisions in Long-Term Planning and Reinforcement Learning—0
SATURN: SAT-based Reinforcement Learning to Unleash Language Model ReasoningCode0
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL—0
Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives—0
Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One—0
Reward Is Enough: LLMs Are In-Context Reinforcement Learners—0
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning—0
Learning-based Autonomous Oversteer Control and Collision Avoidance—0
Show:102550
← PrevPage 252 of 1512Next →

Benchmark Results

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