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 3571–3580 of 15113 papers

TitleStatusHype
Design and Experimental Test of Datatic Approximate Optimal Filter in Nonlinear Dynamic Systems—0
Deep Reinforcement Learning for Asset Allocation in US Equities—0
Deep Reinforcement Learning for Asset Allocation: Reward Clipping—0
A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning—0
Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning—0
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning—0
A statistical learning strategy for closed-loop control of fluid flows—0
Deep Reinforcement Learning for Autonomous Driving: A Survey—0
Deep Reinforcement Learning for Backup Strategies against Adversaries—0
A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning—0
Show:102550
← PrevPage 358 of 1512Next →

Benchmark Results

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