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 2951–2960 of 15113 papers

TitleStatusHype
AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning—0
Decision SpikeFormer: Spike-Driven Transformer for Decision Making—0
A Theory of Abstraction in Reinforcement Learning—0
A Theoretical Connection Between Statistical Physics and Reinforcement Learning—0
A Hybrid Approach Between Adversarial Generative Networks and Actor-Critic Policy Gradient for Low Rate High-Resolution Image Compression—0
A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes—0
A Human Mixed Strategy Approach to Deep Reinforcement Learning—0
Adaptive Actor-Critic Based Optimal Regulation for Drift-Free Uncertain Nonlinear Systems—0
A Tensor Network Approach to Finite Markov Decision Processes—0
A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning—0
Show:102550
← PrevPage 296 of 1512Next →

Benchmark Results

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