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 841–850 of 15113 papers

TitleStatusHype
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum GamesCode1
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement LearningCode1
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk DecodingCode1
Combinatorial Optimization with Policy Adaptation using Latent Space SearchCode1
Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement LearningCode1
Collision Probability Distribution Estimation via Temporal Difference LearningCode1
Learning to Manipulate Deformable Objects without DemonstrationsCode1
Learning to combine primitive skills: A step towards versatile robotic manipulationCode1
Combining Deep Reinforcement Learning and Search for Imperfect-Information GamesCode1
A Traffic Light Dynamic Control Algorithm with Deep Reinforcement Learning Based on GNN PredictionCode1
Show:102550
← PrevPage 85 of 1512Next →

Benchmark Results

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