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 4021–4030 of 15113 papers

TitleStatusHype
Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling—0
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach—0
A Closer Look at Reward Decomposition for High-Level Robotic Explanations—0
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning—0
A Coarse to Fine Question Answering System based on Reinforcement Learning—0
A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers—0
A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition—0
A note on stabilizing reinforcement learning—0
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning—0
A Comparative Analysis of Deep Reinforcement Learning-enabled Freeway Decision-making for Automated Vehicles—0
Show:102550
← PrevPage 403 of 1512Next →

Benchmark Results

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