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 161–170 of 15113 papers

TitleStatusHype
CodeContests+: High-Quality Test Case Generation for Competitive Programming—0
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models—0
Safe Planning and Policy Optimization via World Model Learning—0
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout ReplayCode1
Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning—0
Dissecting Long Reasoning Models: An Empirical StudyCode0
Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning—0
On the Mechanism of Reasoning Pattern Selection in Reinforcement Learning for Language Models—0
Latent Guided Sampling for Combinatorial OptimizationCode0
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning—0
Show:102550
← PrevPage 17 of 1512Next →

Benchmark Results

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