Shimada, K;
Bentley, P;
(2018)
Learning how to flock: Deriving individual behaviour from collective behaviour with multi-agent reinforcement learning and natural evolution strategies.
In:
Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion.
(pp. pp. 169-170).
ACM: Kyoto, Japan.
Preview |
Text
Bentley_Learning how to flock. Deriving individual behaviour from collective behaviour with multi-agent reinforcement learning and natural evolution strategies_AAM.pdf - Accepted Version Download (462kB) | Preview |
Abstract
This work proposes a method for predicting the internal mechanisms of individual agents using observed collective behaviours by multi-agent reinforcement learning (MARL). Since the emergence of group behaviour among many agents can undergo phase transitions, and the action space will not in general be smooth, natural evolution strategies were adopted for updating a policy function. We tested the approach using a well-known flocking algorithm as a target model for our system to learn. With the data obtained from this rule-based model, the MARL model was trained, and its acquired behaviour was compared to the original. In the process, we discovered that agents trained by MARL can self-organize flow patterns using only local information. The expressed pattern is robust to changes in the initial positions of agents, whilst being sensitive to the training conditions used.
| Type: | Proceedings paper |
|---|---|
| Title: | Learning how to flock: Deriving individual behaviour from collective behaviour with multi-agent reinforcement learning and natural evolution strategies |
| Event: | GECCO '18 Companion |
| Location: | Kyoto, Japan |
| Dates: | 15th-19th July 2018 |
| ISBN-13: | 978-1-4503-5764-7 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3205651.3205770 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Multi-agent systems, Reinforcement learning, Swarm intelligence, Evolution strategies, Neural networks/Deep Learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10068107 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
