| Paper: | PS-1A.21 | ||
| Session: | Poster Session 1A | ||
| Location: | H Lichthof | ||
| Session Time: | Saturday, September 14, 16:30 - 19:30 | ||
| Presentation Time: | Saturday, September 14, 16:30 - 19:30 | ||
| Presentation: | Poster | ||
| Publication: | 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany | ||
| Paper Title: | Action Grammars: A Cognitive Model for Learning Temporal Abstractions | ||
| Manuscript: | Click here to view manuscript | ||
| License: |  This work is licensed under a Creative Commons Attribution 3.0 Unported License. |
||
| DOI: | https://doi.org/10.32470/CCN.2019.1258-0 | ||
| Authors: | Robert Tjarko Lange, Einstein Center for Neurosciences Berlin, Germany; Aldo Faisal, Imperial College London, United Kingdom | ||
| Abstract: | Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase and lack semantic interpretability. Human infants, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. In this work we propose a cognitive-inspired Reinforcement Learning architecture which uses grammar induction to identify sub-goal policies. More specifically, by treating an on-policy trajectory as a sentence sampled from the policy-conditioned language of the environment, we identify hierarchical constituents with the help of unsupervised grammatical inference. The resulting set of temporal abstractions is called action grammars (Pastra & Aloimonos, 2012) and can be used to enable efficient imitation, transfer and online learning. | ||