Skip to Main content Skip to Navigation
Conference papers

Transferring Models in Hybrid Reinforcement Learning Agents

Abstract : The main objective of transfer learning is to reuse knowledge acquired in a previous learned task, in order to enhance the learning procedure in a new and more complex task. Transfer learning comprises a suitable solution for speeding up the learning procedure in Reinforcement Learning tasks. In this work, we propose a novel method for transferring models to a hybrid reinforcement learning agent. The models of the transition and reward functions of a source task, will be transferred to a relevant but different target task. The learning algorithm of the target task’s agent takes a hybrid approach, implementing both model-free and model-based learning, in order to fully exploit the presence of a model. The empirical evaluation, of the proposed approach, demonstrated significant results and performance improvements in the 3D Mountain Car task, by successfully using the models generated from the standard 2D Mountain Car.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01571355
Contributor : Hal Ifip <>
Submitted on : Wednesday, August 2, 2017 - 11:41:45 AM
Last modification on : Thursday, March 5, 2020 - 5:42:33 PM

File

978-3-642-23957-1_19_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Anestis Fachantidis, Ioannis Partalas, Grigorios Tsoumakas, Ioannis Vlahavas. Transferring Models in Hybrid Reinforcement Learning Agents. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.162-171, ⟨10.1007/978-3-642-23957-1_19⟩. ⟨hal-01571355⟩

Share

Metrics

Record views

91

Files downloads

172