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 1051–1060 of 15113 papers

TitleStatusHype
Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingCode2
Improving thermal state preparation of Sachdev-Ye-Kitaev model with reinforcement learning on quantum hardwareCode0
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?—0
GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code GenerationCode0
Solving Finite-Horizon MDPs via Low-Rank Tensors—0
PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPUCode0
From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation—0
RE-POSE: Synergizing Reinforcement Learning-Based Partitioning and Offloading for Edge Object Detection—0
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models—0
Reinforcement Learning-Enhanced Procedural Generation for Dynamic Narrative-Driven AR Experiences—0
Show:102550
← PrevPage 106 of 1512Next →

Benchmark Results

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