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 4151–4160 of 15113 papers

TitleStatusHype
Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction—0
Robust Policy Optimization in Deep Reinforcement LearningCode0
Quantum Control based on Deep Reinforcement Learning—0
Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand SystemsCode1
Cross-Domain Transfer via Semantic Skill Imitation—0
Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning—0
Efficient Exploration in Resource-Restricted Reinforcement Learning—0
Explaining Agent's Decision-making in a Hierarchical Reinforcement Learning Scenario—0
Improving generalization in reinforcement learning through forked agents—0
A Review of Off-Policy Evaluation in Reinforcement Learning—0
Show:102550
← PrevPage 416 of 1512Next →

Benchmark Results

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