Importance sampling in reinforcement learning with an estimated behavior policy

DOI10.1007/s10994-020-05938-9OpenAlexW3161040011MaRDI QIDQ2051319

Yanyan Li

Publication date: 24 November 2021

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-020-05938-9

zbMATH Keywords

importance samplingreinforcement learningpolicy evaluation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control

Uses Software

• OpenAI Gym
• Adam
• GitHub
• Baselines

Cites Work

• Doubly robust policy evaluation and optimization
• Integral approximation by kernel smoothing
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator
• Introduction to Information Retrieval
• Importance Sampling Via the Estimated Sampler
• Model-Based Direct Adjustment
• Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score
• Control Functionals for Monte Carlo Integration
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Importance sampling in reinforcement learning with an estimated behavior policy