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 1231–1240 of 15113 papers

TitleStatusHype
Reinforcement Learning with Dynamic Convex Risk MeasuresCode1
Lane Change Decision-Making through Deep Reinforcement LearningCode1
Safety and Liveness Guarantees through Reach-Avoid Reinforcement LearningCode1
Learning to Walk with Dual Agents for Knowledge Graph ReasoningCode1
Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving PoliciesCode1
Direct Behavior Specification via Constrained Reinforcement LearningCode1
A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with DroneCode1
Maximum Entropy Population-Based Training for Zero-Shot Human-AI CoordinationCode1
Variational Quantum Soft Actor-CriticCode1
Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlCode1
Show:102550
← PrevPage 124 of 1512Next →

Benchmark Results

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