Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning

DOI10.1613/JAIR.1.13326MaRDI QIDQ5076329zbMATH OpenOpenAlexWikidataFDO

Authors Yuexiang Zhai, Christina Baek, Zhengyuan Zhou, Jiantao Jiao, Yi Ma

Publication date 16 May 2022

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2107.03961

zbMATH Keywords

planningreinforcement learningtheorem proving

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Reinforcement learning in sparse-reward environments with hindsight policy gradients
• The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms
• Induction and exploitation of subgoal automata for reinforcement learning
• Reward-respecting subtasks for model-based reinforcement learning
• scientific article; zbMATH DE number 1931843

Cites work

• Algorithms for reinforcement learning.
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Deep learning
• scientific article; zbMATH DE number 1315585 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 1560499 (Why is no real title available?)
• scientific article; zbMATH DE number 2086978 (Why is no real title available?)
• scientific article; zbMATH DE number 783783 (Why is no real title available?)
• Planning Algorithms
• Quantitative multi-objective verification for probabilistic systems
• Recent advances in hierarchical reinforcement learning
• Reinforcement learning. An introduction
• Stochastic dynamic programming with factored representations

Describes a project that uses

Uses Software

• MiniGrid
• OpenAI Gym

This page was built for publication: Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5076329)