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 601–625 of 15113 papers

TitleStatusHype
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingCode1
Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes—0
Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making—0
Development of a PPO-Reinforcement Learned Walking Tripedal Soft-Legged Robot using SOFACode0
Towards Optimal Differentially Private Regret Bounds in Linear MDPs—0
Efficient Implementation of Reinforcement Learning over Homomorphic Encryption—0
Deep Distributional Learning with Non-crossing Quantile Network—0
Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion—0
Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and ChallengesCode0
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language ModelsCode2
RL-based Control of UAS Subject to Significant Disturbance—0
Deep Reinforcement Learning for Day-to-day Dynamic Tolling in Tradable Credit Schemes—0
Genetic Programming with Reinforcement Learning Trained Transformer for Real-World Dynamic Scheduling Problems—0
Perception-R1: Pioneering Perception Policy with Reinforcement LearningCode3
Echo Chamber: RL Post-training Amplifies Behaviors Learned in PretrainingCode1
VLM-R1: A Stable and Generalizable R1-style Large Vision-Language ModelCode9
Kimi-VL Technical ReportCode5
Boosting Universal LLM Reward Design through the Heuristic Reward Observation Space Evolution—0
Fast Adaptation with Behavioral Foundation Models—0
Harnessing Equivariance: Modeling Turbulence with Graph Neural NetworksCode1
Better Decisions through the Right Causal World Model—0
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement LearningCode1
TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning—0
Trust-Region Twisted Policy ImprovementCode0
Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning IncentivizationCode2
Show:102550
← PrevPage 25 of 605Next →

Benchmark Results

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