Abstract
Behavioural cloning is an imitation learning technique that teaches an agent how to behave via expert demonstrations. Recent approaches use self-supervision of fully-observable unlabelled snapshots of the states to decode state pairs into actions. However, the iterative learning scheme employed by these techniques is prone to get trapped into bad local minima. Previous work uses goal-aware strategies to solve this issue. However, this requires manual intervention to verify whether an agent has reached its goal. We address this limitation by incorporating a discriminator into the original framework, offering two key advantages and directly solving a learning problem previous work had. First, it disposes of the manual intervention requirement. Second, it helps in learning by guiding function approximation based on the state transition of the expert's trajectories. Third, the discriminator solves a learning issue commonly present in the policy model, which is to sometimes perform a 'no action' within the environment until the agent finally halts.
Original language | English |
---|---|
Title of host publication | 2023 International Joint Conference on Neural Networks (IJCNN) |
Subtitle of host publication | 18-23 June 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781665488679 |
ISBN (Print) | 978-1-6654-8868-6 |
DOIs | |
Publication status | Published - 2 Aug 2023 |
Event | 2023 International Joint Conference on Neural Networks, IJCNN 2023 - Gold Coast, Australia Duration: 18 Jun 2023 → 23 Jun 2023 |
Conference
Conference | 2023 International Joint Conference on Neural Networks, IJCNN 2023 |
---|---|
Country/Territory | Australia |
City | Gold Coast |
Period | 18/06/23 → 23/06/23 |
Bibliographical note
This work was supported by UK Research and Innovation [grant number EP/S023356/1], in the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence (www.safeandtrustedai.org) and made possible via King’s Computational Research, Engineering and Technology Environment (CREATE) [27].Keywords
- Adversarial Learning
- Imitation Learning
- Learning from Observation
- Self-Supervised Learning