Learning to Navigate in Complex Environments

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and task performance can be dramatically improved by relying on additional auxiliary tasks leveraging multimodal sensory inputs. In particular we consider jointly learning the goal-driven reinforcement learning problem with auxiliary depth prediction and loop closure classification tasks. This approach can learn to navigate from raw sensory input in complicated 3D mazes, approaching human-level performance even under conditions where the goal location changes frequently. We provide detailed analysis of the agent behaviour, its ability to localise, and its network activity dynamics, showing that the agent implicitly learns key navigation abilities.

[1]  G. Handelmann,et al.  Hippocampus, space, and memory , 1979 .

[2]  S. C. Suddarth,et al.  Rule-Injection Hints as a Means of Improving Network Performance and Learning Time , 1990, EURASIP Workshop.

[3]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[4]  Hugh F. Durrant-Whyte,et al.  A solution to the simultaneous localization and map building (SLAM) problem , 2001, IEEE Trans. Robotics Autom..

[5]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[6]  Marc'Aurelio Ranzato,et al.  Dynamic auto-encoders for semantic indexing , 2010 .

[7]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Jürgen Schmidhuber,et al.  Evolving large-scale neural networks for vision-based reinforcement learning , 2013, GECCO '13.

[9]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[10]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[11]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[12]  Jianfeng Gao,et al.  Recurrent Reinforcement Learning: A Hybrid Approach , 2015, ArXiv.

[13]  Yann LeCun,et al.  Stacked What-Where Auto-encoders , 2015, ArXiv.

[14]  Regina Barzilay,et al.  Language Understanding for Text-based Games using Deep Reinforcement Learning , 2015, EMNLP.

[15]  Shane Legg,et al.  Massively Parallel Methods for Deep Reinforcement Learning , 2015, ArXiv.

[16]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[17]  Peter Stone,et al.  Deep Recurrent Q-Learning for Partially Observable MDPs , 2015, AAAI Fall Symposia.

[18]  Ming Liu,et al.  Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots , 2016, ArXiv.

[19]  Samuel Gershman,et al.  Deep Successor Reinforcement Learning , 2016, ArXiv.

[20]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

[21]  T. Barron,et al.  Deep Reinforcement Learning in a 3-D Blockworld Environment , 2016 .

[22]  Honglak Lee,et al.  Control of Memory, Active Perception, and Action in Minecraft , 2016, ICML.

[23]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[24]  Sergio Gomez Colmenarejo,et al.  Hybrid computing using a neural network with dynamic external memory , 2016, Nature.

[25]  Kibok Lee,et al.  Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification , 2016, ICML.

[26]  Xinyun Chen.  Under Review as a Conference Paper at Iclr 2017 Delving into Transferable Adversarial Ex- Amples and Black-box Attacks , 2016 .

[27]  Shane Legg,et al.  DeepMind Lab , 2016, ArXiv.

[28]  Shie Mannor,et al.  A Deep Hierarchical Approach to Lifelong Learning in Minecraft , 2016, AAAI.

[29]  Ali Farhadi,et al.  Target-driven visual navigation in indoor scenes using deep reinforcement learning , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[30]  Tom Schaul,et al.  Reinforcement Learning with Unsupervised Auxiliary Tasks , 2016, ICLR.

[31]  Guillaume Lample,et al.  Playing FPS Games with Deep Reinforcement Learning , 2016, AAAI.