Language GANs Falling Short
Journal ref ICLR 2020 - Proceedings of the Seventh International Conference on Learning Representation
作者
Joelle Pineau
Reinforcement Learning
Deep Generative Modeling of LiDAR Data
Comments Presented at IROS 2019
Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift
Comments Accepted at NeurIPS 2019 workshop on Deep Reinforcement Learning
Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking
Comments Accepted at AAAI 2020. Code: https://github.com/e2crawfo/silot. Visualizations: https://sites.google.com/view/silot
No Press Diplomacy: Modeling Multi-Agent Gameplay
Comments Accepted at NeurIPS 2019
Benchmarking Batch Deep Reinforcement Learning Algorithms
Comments Deep RL Workshop NeurIPS 2019
Leveraging exploration in off-policy algorithms via normalizing flows
Comments Accepted to 3rd Conference on Robot Learning (CoRL 2019); Keywords: Exploration, soft actor-critic, normalizing flow, off-policy; maximum entropy, reinforcement learning; deceptive reward; sparse reward; inverse autoregressive flow
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text
Comments Accepted at EMNLP 2019, 9 page content + Appendix
Randomized Value Functions via Multiplicative Normalizing Flows
Journal ref UAI 2019: Conference on Uncertainty in Artificial Intelligence 2019
Separating value functions across time-scales
Comments Full version accepted to ICML 2019. Extended abstract also to be presented at RLDM 2019
Recurrent Value Functions
Temporal Regularization in Markov Decision Process
Comments Published as a conference paper at NIPS 2018
On the Pitfalls of Measuring Emergent Communication
Comments AAMAS 2019. 13 pages
On-line Adaptative Curriculum Learning for GANs
Comments Accepted to the Thirty-Third AAAI Conference On Artificial Intelligence, 2019 (Added 128x128 CelebA samples to the end of the appendix)
Journal ref Proceedings of 33rd AAAI Conference on Artificial Intelligence (AAAI 2019)
On overfitting and asymptotic bias in batch reinforcement learning with partial observability
Comments Accepted at the Journal of Artificial Intelligence Research (JAIR) - 31 pages
The Second Conversational Intelligence Challenge (ConvAI2)
Deep Reinforcement Learning that Matters
Comments Accepted to the Thirthy-Second AAAI Conference On Artificial Intelligence (AAAI), 2018
An Introduction to Deep Reinforcement Learning
Journal ref Foundations and Trends in Machine Learning: Vol. 11, No. 3-4, 2018
Combined Reinforcement Learning via Abstract Representations
Comments Accepted to the Thirty-Third AAAI Conference On Artificial Intelligence, 2019
Natural Environment Benchmarks for Reinforcement Learning
Comments 12 figures
Compositional Language Understanding with Text-based Relational Reasoning
Comments 4 pages of main content, to be presented at Relational Representation Learning Workshop, NIPS 2018, Montreal
The RLLChatbot: a solution to the ConvAI challenge
Comments 46 pages including references and appendix, 14 figures, 12 tables; Under review for the Dialogue & Discourse journal
Reward Estimation for Variance Reduction in Deep Reinforcement Learning
Comments Version 1 as appears in the International Conference on Learning Representations (ICLR) 2018 Workshop Track; Version 2 as appears in the Proceedings of The 2nd Conference on Robot Learning
Adversarial Gain
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
Comments Accepted at the European Workshop on Reinforcement Learning 2018 (EWRL14)
Extending Neural Generative Conversational Model using External Knowledge Sources
Comments Accepted in EMNLP 2018
Sequential Coordination of Deep Models for Learning Visual Arithmetic
The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach
Comments 26 pages, 2 figures, 4 tables
A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
Comments 20 pages, 16 figures
Focused Hierarchical RNNs for Conditional Sequence Processing
Comments To appear at ICML 2018
