Joelle Pineau: Reproducibility, Reusability, and Robustness in Deep Reinforcement Learning ICLR 2018
Abstract: In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning. However reproducing results for state-of-the-art deep RL methods is seldom straightforward. High variance of some methods can make learning particularly difficult when environments or rewards are strongly stochastic. Furthermore, results can be brittle to even minor perturbations in the domain or experimental procedure. In this talk, I will discuss challenges that arise in experimental techniques and reporting procedures in deep RL, and will suggest methods and guidelines to make future results more reproducible, reusable and robust. I will also report on findings from the ICLR 2018 reproducibility challenge.
http://www.cs.mcgill.ca/~jpineau/
Видео Joelle Pineau: Reproducibility, Reusability, and Robustness in Deep Reinforcement Learning ICLR 2018 канала Steven Van Vaerenbergh
http://www.cs.mcgill.ca/~jpineau/
Видео Joelle Pineau: Reproducibility, Reusability, and Robustness in Deep Reinforcement Learning ICLR 2018 канала Steven Van Vaerenbergh
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Fireside Chat with Daphne Koller (ICLR 2018)Bernhard Schölkopf: Learning Causal Mechanisms (ICLR invited talk)Ian Goodfellow: Generative Adversarial Networks (NIPS 2016 tutorial)Canada’s Artificial Intelligence Revolution - Dr. Joelle PineauYee Whye Teh: On Bayesian Deep Learning and Deep Bayesian Learning (NIPS 2017 Keynote)Susan Athey: Counterfactual Inference (NeurIPS 2018 Tutorial)Variational Inference: Foundations and Modern Methods (NIPS 2016 tutorial)Deep Reinforcement Learning in the Enterprise: Bridging the Gap from Games to IndustryYikang Shen: Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (ICLR2019)A History of Reinforcement Learning - Prof. A.G. BartoIan Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)MIT Sloan: Intro to Machine Learning (in 360/VR)Christopher D Manning: A Neural Network Model That Can Reason (ICLR 2018 invited talk)Keynote David Silver NIPS 2017 Deep Reinforcement Learning Symposium AlphaZeroGoogle's Deep Mind Explained! - Self Learning A.I.Prof. Joelle Pineau - The Basics of Reinforcement Learning[ ICLR 2019 ] International Conference on Learning Representations - May 8 - part 6An introduction to Reinforcement LearningProbabilistic Machine Learning - Prof. Zoubin GhahramaniBenjamin Recht: Optimization Perspectives on Learning to Control (ICML 2018 tutorial)