Skip to Main content Skip to Navigation
Conference papers

Transfer Reinforcement Learning with Shared Dynamics

Romain Laroche 1 Merwan Barlier 1, 2
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : This article addresses a particular Transfer Reinforcement Learning (RL) problem: when dynamics do not change from one task to another, and only the reward function does. Our method relies on two ideas, the first one is that transition samples obtained from a task can be reused to learn on any other task: an immediate reward estimator is learnt in a supervised fashion and for each sample, the reward entry is changed by its reward estimate. The second idea consists in adopting the optimism in the face of uncertainty principle and to use upper bound reward estimates. Our method is tested on a navigation task, under four Transfer RL experimental settings: with a known reward function, with strong and weak expert knowledge on the reward function, and with a completely unknown reward function. It is also evaluated in a Multi-Task RL experiment and compared with the state-of-the-art algorithms. Results reveal that this method constitutes a major improvement for transfer/multi-task problems that share dynamics.
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download
Contributor : Merwan Barlier Connect in order to contact the contributor
Submitted on : Wednesday, August 9, 2017 - 4:34:44 PM
Last modification on : Friday, December 11, 2020 - 6:44:05 PM
Long-term archiving on: : Wednesday, January 17, 2018 - 8:24:08 PM


Files produced by the author(s)




  • HAL Id : hal-01548649, version 1


Romain Laroche, Merwan Barlier. Transfer Reinforcement Learning with Shared Dynamics. AAAI-17 - Thirty-First AAAI Conference on Artificial Intelligence, Feb 2017, San Francisco, United States. pp.7. ⟨hal-01548649⟩



Record views


Files downloads