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 1–10 of 15113 papers

TitleStatusHype
From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning—0
VAR-MATH: Probing True Mathematical Reasoning in Large Language Models via Symbolic Multi-Instance Benchmarks—0
Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback—0
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation—0
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities—0
Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)—0
Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models—0
Kevin: Multi-Turn RL for Generating CUDA Kernels—0
Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training—0
High-Throughput Distributed Reinforcement Learning via Adaptive Policy SynchronizationCode0
Show:102550
← PrevPage 1 of 1512Next →

Benchmark Results

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