Abstract
Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. How- ever, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them.
Original language | English |
---|---|
Title of host publication | 27th European Conference on Artificial Intelligence |
Publisher | IOS Press |
Number of pages | 7 |
Publication status | Published - 5 Jul 2024 |
Event | European Conference On Artificial Intelligence - Santiago de Compostela, Spain Duration: 19 Oct 2024 → 24 Oct 2024 Conference number: 27 https://www.ecai2024.eu/ |
Conference
Conference | European Conference On Artificial Intelligence |
---|---|
Abbreviated title | ECAI |
Country/Territory | Spain |
City | Santiago de Compostela |
Period | 19/10/2024 → 24/10/2024 |
Internet address |
Keywords
- Imitation Learning
- Exploration