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 321–330 of 15113 papers

TitleStatusHype
Reward-Aware Proto-Representations in Reinforcement Learning—0
Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning—0
DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation—0
Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOCode4
LARES: Latent Reasoning for Sequential Recommendation—0
Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsCode1
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking RewardCode2
Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning—0
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement LearningCode3
Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only—0
Show:102550
← PrevPage 33 of 1512Next →

Benchmark Results

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