Abstract
Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty. For example, the reward can be the negative entropy of the agent's belief over an unknown (or hidden) variable. Typically, the rewards of an RL agent are defined as a function of the state-action pairs and not as a function of the belief of the agent; this hinders the direct application of deep RL methods for such tasks. This paper tackles the challenge of using belief-based rewards for a deep RL agent, by offering a simple insight that maximizing any convex function of the belief of the agent can be approximated by instead maximizing a prediction reward: a reward based on prediction accuracy. In particular, we derive the exact error between negative entropy and the expected prediction reward. This insight provides theoretical motivation for several fields using prediction rewards---namely visual attention, question answering systems, and intrinsic motivation---and highlights their connection to the usually distinct fields of active perception, active sensing, and sensor placement. Based on this insight we present deep anticipatory networks (DANs), which enables an agent to take actions to reduce its uncertainty without performing explicit belief inference. We present two applications of DANs: building a sensor selection system for tracking people in a shopping mall and learning discrete models of attention on fashion MNIST and MNIST digit classification.
Original language | English |
---|---|
Title of host publication | Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 |
Editors | Bo An, Amal El Fallah Seghrouchni, Gita Sukthankar |
Place of Publication | Richland, SC |
Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
Pages | 1215–1223 |
Number of pages | 9 |
ISBN (Electronic) | 9781450375184 |
ISBN (Print) | 9781450375184 |
Publication status | Published - 9 May 2020 |
Event | AAMAS 2020: The 19th International Conference on Autonomous Agents and Multi-Agent Systems - Auckland, New Zealand Duration: 9 May 2020 → 13 May 2020 Conference number: 19th https://aamas2020.conference.auckland.ac.nz |
Publication series
Name | Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS |
---|---|
Volume | 2020-May |
ISSN (Print) | 1548-8403 |
ISSN (Electronic) | 1558-2914 |
Conference
Conference | AAMAS 2020 |
---|---|
Country/Territory | New Zealand |
City | Auckland |
Period | 9/05/20 → 13/05/20 |
Other | Virtual/online event due to COVID-19 |
Internet address |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- Information gain
- Partially observability
- Reinforcement learning