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 3931–3940 of 15113 papers

TitleStatusHype
Model-free reinforcement learning with noisy actions for automated experimental control in opticsCode0
Human-in-the-loop Reinforcement Learning for Data Quality Monitoring in Particle Physics Experiments—0
Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine—0
Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning—0
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee—0
Embedding-Aligned Language Models—0
Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality—0
Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of ExperiencesCode0
Offline Reinforcement Learning from Datasets with Structured Non-StationarityCode0
A finite time analysis of distributed Q-learning—0
Show:102550
← PrevPage 394 of 1512Next →

Benchmark Results

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