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 2781–2790 of 15113 papers

TitleStatusHype
Staged Reinforcement Learning for Complex Tasks through Decomposed Environments—0
Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models—0
AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction EstimationCode1
Imitation Bootstrapped Reinforcement Learning—0
Hierarchical Reinforcement Learning for Power Network Topology ControlCode1
Using General Value Functions to Learn Domain-Backed Inventory Management Policies—0
Towards model-free RL algorithms that scale well with unstructured data—0
State-Wise Safe Reinforcement Learning With Pixel ObservationsCode1
Domain Randomization via Entropy Maximization—0
Energy Efficiency Optimization for Subterranean LoRaWAN Using A Reinforcement Learning Approach: A Direct-to-Satellite Scenario—0
Show:102550
← PrevPage 279 of 1512Next →

Benchmark Results

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