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 4391–4400 of 15113 papers

TitleStatusHype
A Finite-Sample Analysis of Distributionally Robust Average-Reward Reinforcement Learning—0
A finite time analysis of distributed Q-learning—0
A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation—0
A First-Occupancy Representation for Reinforcement Learning—0
A Flexible Measurement of Diversity in Datasets with Random Network Distillation—0
A Framework and Method for Online Inverse Reinforcement Learning—0
A Framework for Constrained and Adaptive Behavior-Based Agents—0
Scaling data-driven robotics with reward sketching and batch reinforcement learning—0
A Framework for dynamically meeting performance objectives on a service mesh—0
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation—0
Show:102550
← PrevPage 440 of 1512Next →

Benchmark Results

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