Deep imitation learning for 3D navigation tasks
- Submitting institution
-
Teesside University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 8283480
- Type
- D - Journal article
- DOI
-
10.1007/s00521-017-3241-z
- Title of journal
- Neural Computing and Applications
- Article number
- -
- First page
- 389
- Volume
- 29
- Issue
- 7
- ISSN
- 0941-0643
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work proposes novel algorithms for deep active imitation learning and combing learning from demonstrations and experience using deep networks. This research provides insights into how a generic learning process can be used to learn from raw data without prior knowledge of the task. The experimentation and comparison with state-of-the-art methods such as deep-Q-networks (DQN) and Asynchronous actor-critic (A3C) learning show that the proposed approaches are effective and efficient in 3D navigation tasks. The work has been developed in further publications (e.g., Faria et al, 2019, 10.1109/ICTAI.2019.00242, Faria et al, 2018, 10.1109/ICMLA.2019.00043, Ejaz et al, 2019, 10.1109/SCORED.2019.8896352).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -