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 451–460 of 15113 papers

TitleStatusHype
ACN-Sim: An Open-Source Simulator for Data-Driven Electric Vehicle Charging ResearchCode1
Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement LearningCode1
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning AgentsCode1
Co-Reinforcement Learning for Unified Multimodal Understanding and GenerationCode1
Contrastive Preference Learning: Learning from Human Feedback without RLCode1
Counterfactual Data Augmentation using Locally Factored DynamicsCode1
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLCode1
Contrastive Active InferenceCode1
Critic Regularized RegressionCode1
A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise DatasetsCode1
Show:102550
← PrevPage 46 of 1512Next →

Benchmark Results

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