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 2121–2130 of 15113 papers

TitleStatusHype
Improving Offline Reinforcement Learning with Inaccurate Simulators—0
Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows—0
Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement LearningCode2
Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints—0
UDUC: An Uncertainty-driven Approach for Learning-based Robust Control—0
CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple CriticsCode0
Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning—0
Proximal Curriculum with Task Correlations for Deep Reinforcement LearningCode0
Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning—0
A Model-based Multi-Agent Personalized Short-Video Recommender System—0
Show:102550
← PrevPage 213 of 1512Next →

Benchmark Results

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