Fetching the paper…

Reading the bibliography…

2021

Physical Reasoning Using Dynamics-Aware Models

Ahmed, Eltayeb, Bakhtin, Anton, van der Maaten, Laurens et al.

Original
PDF
Post on X

Understand

A common approach to solving physical reasoning tasks is to train a value learner on example tasks.

A limitation of such an approach is that it requires learning about object dynamics solely from reward values assigned to the final state of a rollout of the environment.
This study aims to address this limitation by augmenting the reward value with self-supervised signals about object dynamics.
Specifically, we train the model to characterize the similarity of two environment rollouts, jointly with predicting the outcome of the reasoning task.

Physical Reasoning Using Dynamics-Aware Models · Around

Built on

Playing atari with deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, D. P. and Ba, J · 2015
Earlier work this paper cites.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Earlier work this paper cites.
SGDR: Stochastic gradient descent with warm restarts
Loshchilov, I. and Hutter, H · 2016
Earlier work this paper cites.

Similar

Representation learning with contrastive predictive coding
Original
Oord, A. v. d., Li, Y., and Vinyals, O · 2018
Cited alongside, same era.
Film: Visual reasoning with a general conditioning layer
Perez, E., Strub, F., De Vries, H., Dumoulin, V., and Courville, A · 2018
Cited alongside, same era.
PHYRE: A new benchmark for physical reasoning
Bakhtin, A., van der Maaten, L., Johnson, J., Gustafson, L., and Girshick, R · 2019
Cited alongside, same era.
The Tools challenge: Rapid trial-and-error learning in physical problem solving
Allen, K. R., Smith, K. A., and Tenenbaum, J. B · 2020
Cited alongside, same era.

Then

Forward prediction for physical reasoning
Original
Girdhar, R., Gustafson, L., Adcock, A., and van der Maaten, L · 2020
Later among the works it cites.
Learning to simulate complex physics with graph networks
Original
Sanchez-Gonzalez, A., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., and Battaglia, P. W · 2020
Later among the works it cites.
Dynamics-aware embeddings
Whitney, W. F., Agarwal, R., Cho, K., and Gupta, A · 2020
Later among the works it cites.
Learning long-term visual dynamics with region proposal interaction networks
Qi, H., Wang, X., Pathak, D., Ma, Y., and Malik, J · 2021
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…