Programmable Agents

We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks.

[1]  Marcin Andrychowicz,et al.  One-Shot Imitation Learning , 2017, NIPS.

[2]  Nando de Freitas,et al.  A Machine Learning Perspective on Predictive Coding with PAQ8 , 2011, 2012 Data Compression Conference.

[3]  Ingo Br,et al.  Prolog programming for artificial intelligence , 1990 .

[4]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[5]  Wei Xu,et al.  A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment , 2017, ArXiv.

[6]  Wojciech Zaremba,et al.  Learning to Execute , 2014, ArXiv.

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

[8]  Martial Hebert,et al.  From Red Wine to Red Tomato: Composition with Context , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Dustin Tran,et al.  Deep Probabilistic Programming , 2017, ICLR.

[10]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[11]  Wojciech Zaremba,et al.  Learning Simple Algorithms from Examples , 2015, ICML.

[12]  Trevor Darrell,et al.  Learning to Reason: End-to-End Module Networks for Visual Question Answering , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[14]  Andrew Y. Ng,et al.  Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[15]  Matthew V. Mahoney,et al.  Adaptive weighing of context models for lossless data compression , 2005 .

[16]  Sergey Levine,et al.  Learning modular neural network policies for multi-task and multi-robot transfer , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

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

[18]  Joshua B. Tenenbaum,et al.  Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation , 2016, NIPS.

[19]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[20]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[21]  Wang Ling,et al.  Learning to Compose Words into Sentences with Reinforcement Learning , 2016, ICLR.

[22]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.

[23]  Quoc V. Le,et al.  Neural Programmer: Inducing Latent Programs with Gradient Descent , 2015, ICLR.

[24]  Guy Lever,et al.  Deterministic Policy Gradient Algorithms , 2014, ICML.

[25]  Nando de Freitas,et al.  Neural Programmer-Interpreters , 2015, ICLR.

[26]  Tim Rocktäschel,et al.  Programming with a Differentiable Forth Interpreter , 2016, ICML.

[27]  Dawn Xiaodong Song,et al.  Making Neural Programming Architectures Generalize via Recursion , 2017, ICLR.

[28]  Wang Ling,et al.  Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems , 2017, ACL.

[29]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[30]  Phil Blunsom,et al.  Learning to Transduce with Unbounded Memory , 2015, NIPS.

[31]  Ufuk Topcu,et al.  Environment-Independent Task Specifications via GLTL , 2017, ArXiv.

[32]  Martín Abadi,et al.  Learning a Natural Language Interface with Neural Programmer , 2016, ICLR.

[33]  Dan Klein,et al.  Neural Module Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Li Fei-Fei,et al.  Inferring and Executing Programs for Visual Reasoning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[35]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[36]  Sebastian Nowozin,et al.  DeepCoder: Learning to Write Programs , 2016, ICLR.

[37]  Pushmeet Kohli,et al.  RobustFill: Neural Program Learning under Noisy I/O , 2017, ICML.

[38]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[39]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[40]  Lukasz Kaiser,et al.  Neural GPUs Learn Algorithms , 2015, ICLR.