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 3051–3060 of 15113 papers

TitleStatusHype
Language Reward Modulation for Pretraining Reinforcement LearningCode1
RamseyRL: A Framework for Intelligent Ramsey Number Counterexample SearchingCode0
Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems—0
LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient QueryingCode0
A Homogenization Approach for Gradient-Dominated Stochastic Optimization—0
Stabilizing Unsupervised Environment Design with a Learned Adversary—0
Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL—0
Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling—0
UAV-assisted Semantic Communication with Hybrid Action Reinforcement Learning—0
Reinforced Self-Training (ReST) for Language Modeling—0
Show:102550
← PrevPage 306 of 1512Next →

Benchmark Results

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