Importance Weighted Transfer of Samples in Reinforcement Learning

Andrea Tirinzoni 1 Andrea Sessa 1 Matteo Pirotta 2 Marcello Restelli 1
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related approaches focus on selecting the most relevant source samples for solving the target task, but then all the transferred samples are used without considering anymore the discrepancies between the task models. In this paper, we propose a model-based technique that automatically estimates the relevance (importance weight) of each source sample for solving the target task. In the proposed approach, all the samples are transferred and used by a batch RL algorithm to solve the target task, but their contribution to the learning process is proportional to their importance weight. By extending the results for importance weighting provided in supervised learning literature, we develop a finite-sample analysis of the proposed batch RL algorithm. Furthermore, we empirically compare the proposed algorithm to state-of-the-art approaches, showing that it achieves better learning performance and is very robust to negative transfer, even when some source tasks are significantly different from the target task.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01941213
Contributor : Matteo Pirotta <>
Submitted on : Friday, November 30, 2018 - 6:34:16 PM
Last modification on : Friday, March 22, 2019 - 1:37:09 AM
Long-term archiving on : Friday, March 1, 2019 - 3:57:33 PM

File

tirinzoni2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01941213, version 1

Citation

Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli. Importance Weighted Transfer of Samples in Reinforcement Learning. ICML 2018 - The 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.4936-4945. ⟨hal-01941213⟩

Share

Metrics

Record views

30

Files downloads

18