Pessimistic value iteration for multi-task data sharing in offline reinforcement learning

DOI10.1016/J.ARTINT.2023.104048MaRDI QIDQ6152665zbMATH OpenFDO

Authors

Publication date 13 February 2024

Published in Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

uncertainty quantificationdata sharingoffline reinforcement learningpessimistic value iteration

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Offline reinforcement learning with representations for actions
• Offline reinforcement learning with task hierarchies
• Exploiting action impact regularity and exogenous state variables for offline reinforcement learning
• Settling the sample complexity of model-based offline reinforcement learning
• Reliable off-policy evaluation for reinforcement learning

Cites work

• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• Entropy-SGD: biasing gradient descent into wide valleys
• Near-optimal regret bounds for reinforcement learning
• Reinforcement learning. An introduction

Cited in

(2)

• Exploiting action impact regularity and exogenous state variables for offline reinforcement learning
• Offline reinforcement learning with representations for actions

This page was built for publication: Pessimistic value iteration for multi-task data sharing in offline reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6152665)