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 3881–3890 of 15113 papers

TitleStatusHype
Deep Transfer Q-Learning for Offline Non-Stationary Reinforcement Learning—0
A Comparative Study of Reinforcement Learning Techniques on Dialogue Management—0
ACTRCE: Augmenting Experience via Teacher’s Advice—0
CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation—0
Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations—0
DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO—0
A General Perspective on Objectives of Reinforcement Learning—0
Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework—0
DeepWiVe: Deep-Learning-Aided Wireless Video Transmission—0
Distributed off-Policy Actor-Critic Reinforcement Learning with Policy Consensus—0
Show:102550
← PrevPage 389 of 1512Next →

Benchmark Results

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