Framing reinforcement learning from human reward: reward positivity, temporal discounting, episodicity, and performance

DOI10.1016/J.ARTINT.2015.03.009MaRDI QIDQ891791zbMATHOpenAlexFDO

Authors N. E. Zubov

Publication date 17 November 2015

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2015.03.009

zbMATH Keywords

reinforcement learningend-user programminghuman teachershuman-agent interactioninteractive machine learningmodeling user behavior

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Reward machines: exploiting reward function structure in reinforcement learning
• On average versus discounted reward temporal-difference learning
• Average reward reinforcement learning: foundations, algorithms, and empirical results
• Risk-sensitive reinforcement learning
• A survey of preference-based reinforcement learning methods

Cites work

• 10.1162/153244303322753616
• A survey of cross-validation procedures for model selection
• Learning Representation and Control in Markov Decision Processes: New Frontiers

Cited in

(2)

• Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective
• TAMER

This page was built for publication: Framing reinforcement learning from human reward: reward positivity, temporal discounting, episodicity, and performance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q891791)