Deep imitation learning for 3D navigation tasks.
Gaber, Mohamed Medhat
MetadataShow full item record
HUSSEIN, A., ELYAN, E., GABER, M.M. and JAYNE, C. . Deep imitation learning for 3D navigation tasks. Neural computing and applications [online], (accepted). Available from: https://doi.org/10.1007/s00521-017-3241-z
Deep learning techniques have shown success in learning from raw high dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: Deep-Q-networks (DQN) and Asynchronous actor critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effiective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.
Permalink for this recordhttp://hdl.handle.net/10059/2543
Collections in which this item appears
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0
Showing items related by title, author, creator and subject.
Hussein, Ahmed; Gaber, Mohamed Medhat; Elyan, Eyad; Jayne, Chrisina (ACM https://doi.org/10.1145/3054912, 2017-04-11)HUSSEIN, A., GABER, M.M., ELYAN, E. and JAYNE, C. 2017 Imitation learning: a suvey of learning methods. ACM computing surveys [online], 50(2), article 21. Available from: https://doi.org/10.1145/3054912Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of ...
The significance of personal learning environments (PLEs) in nursing education: extending current conceptualizations. Patterson, Christopher; Stephens, Moira; Chang, Vico; Price, Ann M.; Work, Fiona; Snelgrove-Clarke, Erna; Harada, Theresa (Elsevier http://dx.doi.org/10.1016/j.nedt.2016.09.010, 2016-09-26)PATTERSON, C., STEPHENS, M. CHANG, V., PRICE, A.M., WORK, F., SNELGROVE-CLARKE, E. and HARADA, T. 2016. The significance of personal learning environments (PLEs) in nursing education: extending current conceptualizations. Nurse education today [online],48, pages 99-105. Available from: http://dx.doi.org/10.1016/j.nedt.2016.09.010Background - Personal learning environments (PLE) have been shown to be a critical part of how students negotiate and manage their own learning. Understandings of PLEs appear to be constrained by narrow definitions that ...
Hussein, Ahmed; Elyan, Eyad; Gaber, Mohamed Medhat; Jayne, Chrisina (IEEE https://doi.org/10.1109/IJCNN.2017.7965896, 2017-05-14)HUSSEIN, A., ELYAN, E., GABER, M.M. and JAYNE, C. 2017. Deep reward shaping from demonstrations. In Proceedings of the International joint conference on neural networks (IJCNN 2017), 14 - 19 May 2017, Anchorage, USA. Piscataway, NJ: IEEE [online], pages 510-517. Available from: https://doi.org/10.1109/IJCNN.2017.7965896Deep reinforcement learning is rapidly gaining attention due to recent successes in a variety of problems. The combination of deep learning and reinforcement learning allows for a generic learning process that does not ...