作者
Joelle Pineau
Reinforcement Learning
Disentangling the independently controllable factors of variation by interacting with the world
Comments Presented at NIPS 2017 Learning Disentangling Representations Workshop
A Deep Reinforcement Learning Chatbot (Short Version)
Comments 9 pages, 1 figure, 2 tables; presented at NIPS 2017, Conversational AI: "Today's Practice and Tomorrow's Potential" Workshop
Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
Comments ACL 2017
Journal ref Proceedings of the 55th annual meeting on Association for Computational Linguistics (2017), pp. 1116-1126
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Comments Accepted to the Thirthy-Second AAAI Conference On Artificial Intelligence (AAAI), 2018
Ethical Challenges in Data-Driven Dialogue Systems
Comments In Submission to the AAAI/ACM conference on Artificial Intelligence, Ethics, and Society
ACtuAL: Actor-Critic Under Adversarial Learning
A Deep Reinforcement Learning Chatbot
Comments 40 pages, 9 figures, 11 tables
Piecewise Latent Variables for Neural Variational Text Processing
Comments 19 pages, 2 figures, 8 tables; EMNLP 2017
Independently Controllable Factors
Streaming kernel regression with provably adaptive mean, variance, and regularization
MACA: A Modular Architecture for Conversational Agents
Comments The architecture needs to be tested further. Sorry for the inconvenience. We should be putting up the paper up soon
Independently Controllable Features
Comments RLDM submission
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
Comments 56 pages including references and appendix, 5 tables and 1 figure; Under review for the Dialogue & Discourse journal. Update: paper has been rewritten and now includes several new datasets
An Actor-Critic Algorithm for Sequence Prediction
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
Comments First 4 authors had equal contribution. 13 pages, 5 tables, 6 figures. EMNLP 2016
Generative Deep Neural Networks for Dialogue: A Short Review
Comments 6 pages, 1 figure, 3 tables; NIPS 2016 workshop on Learning Methods for Dialogue
Bayesian Reinforcement Learning: A Survey
Journal ref Foundations and Trends in Machine Learning, Vol. 8: No. 5-6, pp 359-492, 2015
Learning Robust Features using Deep Learning for Automatic Seizure Detection
Comments Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA
On the Evaluation of Dialogue Systems with Next Utterance Classification
Comments Accepted to SIGDIAL 2016 (short paper). 5 pages
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
Comments SIGDIAL 2015. 10 pages, 5 figures. Update includes link to new version of the dataset, with some added features and bug fixes. See: https://github.com/rkadlec/ubuntu-ranking-dataset-creator
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Comments 15 pages, 5 tables, 4 figures
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Comments 8 pages with references; Published in AAAI 2016 (Special Track on Cognitive Systems)
Conditional Computation in Neural Networks for faster models
Comments ICLR 2016 submission, revised
Practical Kernel-Based Reinforcement Learning
Efficient Learning and Planning with Compressed Predictive States
Comments 45 pages, 10 figures, submitted to the Journal of Machine Learning Research
Representation as a Service
Comments 8 pages
Non-Deterministic Policies in Markovian Decision Processes
Journal ref Journal Of Artificial Intelligence Research, Volume 40, pages 1-24, 2011
Online Planning Algorithms for POMDPs
Journal ref Journal Of Artificial Intelligence Research, Volume 32, pages 663-704, 2008
