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 3761–3770 of 15113 papers

TitleStatusHype
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes—0
Deep Reinforcement Learning: Framework, Applications, and Embedded Implementations—0
Correlation Priors for Reinforcement Learning—0
A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting—0
Assured RL: Reinforcement Learning with Almost Sure Constraints—0
Deep Reinforcement Learning from Policy-Dependent Human Feedback—0
Deep Reinforcement Learning From Raw Pixels in Doom—0
Correlation Filter Selection for Visual Tracking Using Reinforcement Learning—0
Deep reinforcement learning guided graph neural networks for brain network analysis—0
Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework—0
Show:102550
← PrevPage 377 of 1512Next →

Benchmark Results

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