2018

Gated Path Planning Networks

Lee, Lisa, Parisotto, Emilio, Chaplot, Devendra Singh et al.

Understand

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture.

Despite their effectiveness, they suffer from several disadvantages including training instability, random seed sensitivity, and other optimization problems.
In this work, we reframe VINs as recurrent-convolutional networks which demonstrates that VINs couple recurrent convolutions with an unconventional max-pooling activation.
From this perspective, we argue that standard gated recurrent update equations could potentially alleviate the optimization issues plaguing VIN.

Built on

Backpropagation applied to handwritten zip code recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D · 1989
Earlier work this paper cites.
Learning policies for partially observable environments: Scaling up
Littman, M. L., Cassandra, A. R., and Kaelbling, L. P · 1995
Earlier work this paper cites.
Long short-term memory
Hochreiter, S. and Schmidhuber, J · 1997
Earlier work this paper cites.
Cooperative pathfinding
Silver, D · 2005
Earlier work this paper cites.
On the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., and Bengio, Y · 2013
Earlier work this paper cites.
irobot brings visual mapping and navigation to the roomba 980, 2015
Ackerman, E. and Guizzo, E · 2015
Earlier work this paper cites.
Convolutional LSTM network: A machine learning approach for precipitation nowcasting
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., kin Wong, W., and chun Woo, W · 2015
Earlier work this paper cites.

Similar

Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Cited alongside, same era.
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
Kempka, M., Wydmuch, M., Runc, G., Toczek, J., and Jaśkowski, W · 2016
Cited alongside, same era.
Bridging the gaps between residual learning, recurrent neural networks and visual cortex
Original
Liao, Q. and Poggio, T · 2016
Cited alongside, same era.
The predictron: End-to-end learning and planning
Original
Silver, D., van Hasselt, H., Hessel, M., Schaul, T., Guez, A., Harley, T., Dulac-Arnold, G., Reichert, D., Rabinowitz, N., Barreto, A., et al · 2016
Cited alongside, same era.
Cognitive mapping and planning for visual navigation
Gupta, S., Davidson, J., Levine, S., Sukthankar, R., and Malik, J · 2017
Cited alongside, same era.
Hypernetworks
Ha, D., Dai, A. M., and Le, Q. V · 2017
Cited alongside, same era.
QMDP-Net: Deep learning for planning under partial observability
Karkus, P., Hsu, D., and Lee, W. S · 2017
Cited alongside, same era.
Unifying map and landmark based representations for visual navigation
Original
Gupta, S., Fouhey, D. F., Levine, S., and Malik, J
Cited in the paper.

Then

Playing fps games with deep reinforcement learning
Lample, G. and Chaplot, D. S · 2017
Later among the works it cites.
Value prediction network
Oh, J., Singh, S., and Lee, H · 2017
Later among the works it cites.
Value Iteration Networks
Tamar, A., Wu, Y., Thomas, G., Levine, S., and Abbeel, P · 2017
Later among the works it cites.
Feedback networks
Zamir, A. R., Wu, T.-L., Sun, L., Shen, W. B., Shi, B. E., Malik, J., and Savarese, S · 2017
Later among the works it cites.
Active neural localization
Chaplot, D. S., Parisotto, E., and Salakhutdinov, R · 2018
Closest in time.
Maze generation algorithms — Wikipedia, the free encyclopedia, 2018
Maze Generation Algorithms · 2018
Closest in time.
Introduction to Reinforcement Learning
Sutton, R. and Barto, A · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…