Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
This addresses imitation learning in continuous environments by reducing reliance on expert data and manual constraint encoding, though it appears incremental as it builds on existing methods.
The paper tackled the problem of imitation learning requiring many expert trajectories and human intervention for domain constraints by proposing CILO, which incorporates exploration and path signatures; it achieved the best overall performance in five environments, outperforming the expert in two.
Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, 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.