Search Results for author: Victor Bapst

Found 12 papers, 3 papers with code

Object-oriented state editing for HRL

no code implementations31 Oct 2019 Victor Bapst, Alvaro Sanchez-Gonzalez, Omar Shams, Kimberly Stachenfeld, Peter W. Battaglia, Satinder Singh, Jessica B. Hamrick

We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems.

Hamiltonian Graph Networks with ODE Integrators

no code implementations27 Sep 2019 Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, Peter Battaglia

We introduce an approach for imposing physically informed inductive biases in learned simulation models.

Deep reinforcement learning with relational inductive biases

no code implementations ICLR 2019 Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia

We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability.

Relational Reasoning Starcraft +1

Structured agents for physical construction

no code implementations5 Apr 2019 Victor Bapst, Alvaro Sanchez-Gonzalez, Carl Doersch, Kimberly L. Stachenfeld, Pushmeet Kohli, Peter W. Battaglia, Jessica B. Hamrick

Our results show that agents which use structured representations (e. g., objects and scene graphs) and structured policies (e. g., object-centric actions) outperform those which use less structured representations, and generalize better beyond their training when asked to reason about larger scenes.

Scene Understanding

Relational Deep Reinforcement Learning

8 code implementations5 Jun 2018 Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning.

Relational Reasoning Starcraft +1

Relational inductive bias for physical construction in humans and machines

no code implementations4 Jun 2018 Jessica B. Hamrick, Kelsey R. Allen, Victor Bapst, Tina Zhu, Kevin R. McKee, Joshua B. Tenenbaum, Peter W. Battaglia

While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks.

Object Classification

Hyperbolic Attention Networks

no code implementations ICLR 2019 Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.

Machine Translation Question Answering +1

Distral: Robust Multitask Reinforcement Learning

no code implementations NeurIPS 2017 Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu

Moreover, the proposed learning process is more robust and more stable---attributes that are critical in deep reinforcement learning.

Transfer Learning

Sample Efficient Actor-Critic with Experience Replay

9 code implementations3 Nov 2016 Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.

Continuous Control

Cannot find the paper you are looking for? You can Submit a new open access paper.