Only Relevant Information Matters: Filtering Out Noisy Samples To Boost RL

Yannis Flet-Berliac, Pierre‐Marie Preux

Type: Preprint

Publication Date: 2020-07-01

Citations: 3

DOI: https://doi.org/10.24963/ijcai.2020/376

Locations

arXiv (Cornell University) - View - PDF
LillOA (Université de Lille (University Of Lille)) - View - PDF
HAL (Le Centre pour la Communication Scientifique Directe) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Samples Are Useful? Not Always: denoising policy gradient updates using variance explained	2019	Yannis Flet-Berliac Pierre‐Marie Preux
+	Rethinking Exploration for Sample-Efficient Policy Learning.	2021	WILLIAM F. WHITNEY Michael Bloesch Jost Tobias Springenberg Abbas Abdolmaleki Martin Riedmiller
+	Prioritizing Samples in Reinforcement Learning with Reducible Loss	2022	Shivakanth Sujit Somjit Nath Pedro H. M. Braga Samira Ebrahimi Kahou
+	Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning	2021	WILLIAM F. WHITNEY Michael Bloesch Jost Tobias Springenberg Abbas Abdolmaleki Kyunghyun Cho Martin Riedmiller
+	Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning	2021	WILLIAM F. WHITNEY Michael Bloesch Jost Tobias Springenberg Abbas Abdolmaleki Kyunghyun Cho Martin Riedmiller
+ PDF Chat	Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration	2013	Tingting Zhao Hirotaka Hachiya Voot Tangkaratt Jun Morimoto Masashi Sugiyama
+ PDF Chat	Policy Gradient with Active Importance Sampling	2024	Matteo Papini Giorgio Manganini Alberto Maria Metelli Marcello Restelli
+	Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration	2013	Tingting Zhao Hirotaka Hachiya Voot Tangkaratt Jun Morimoto Masashi Sugiyama
+	Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration	2013	Tingting Zhao Hirotaka Hachiya Masashi Sugiyama
+	Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics	2022	Jun Jet Tai Jordan K. Terry Mauro S. Innocente James Brusey Nadjim Horri
+	Local policy search with Bayesian optimization	2021	Sarah Müller Alexander von Rohr Sebastian Trimpe
+	Local policy search with Bayesian optimization	2021	Sarah Müller Alexander von Rohr Sebastian Trimpe
+	Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces	2019	Guy Lorberbom Chris J. Maddison Nicolas Heess Tamir Hazan Daniel Tarlow
+	Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces	2019	Guy Lorberbom Chris J. Maddison Nicolas Heess Tamir Hazan Daniel Tarlow
+	Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation	2022	Vincent Mai Kaustubh Mani Liam Paull
+	How to Enable Uncertainty Estimation in Proximal Policy Optimization	2022	Eugene Bykovets Yannick Metz Mennatallah El‐Assady Daniel A. Keim Joachim M. Buhmann
+	DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning	2020	Rasool Fakoor Pratik Chaudhari Alexander J. Smola
+	The Mirage of Action-Dependent Baselines in Reinforcement Learning	2018	George Tucker Surya Bhupatiraju Shixiang Gu Richard E. Turner Zoubin Ghahramani Sergey Levine
+	Regret Minimization Experience Replay in Off-Policy Reinforcement Learning	2021	Xuhui Liu Zhenghai Xue Jing-Cheng Pang Shengyi Jiang Feng Xu Yang Yu
+ PDF Chat	Regret Minimization Experience Replay in Off-Policy Reinforcement Learning	2021	Xuhui Liu Zhenghai Xue Jing-Cheng Pang Shengyi Jiang Feng Xu Yang Yu

Works That Cite This (3)

Action	Title	Year	Authors
+	Adversarially Guided Actor-Critic	2021	Yannis Flet-Berliac Johan Ferret Olivier Pietquin Pierre‐Marie Preux Matthieu Geist
+ PDF Chat	Learning Value Functions in Deep Policy Gradients using Residual Variance	2021	Yannis Flet-Berliac Reda Ouhamma Odalric-Ambrym Maillard Pierre‐Marie Preux
+ PDF Chat	Adversarially Guided Actor-Critic	2021	Yannis Flet-Berliac Johan Ferret Olivier Pietquin Pierre‐Marie Preux Matthieu Geist

Works Cited by This (20)

Action	Title	Year	Authors
+	High-Dimensional Continuous Control Using Generalized Advantage Estimation	2015	John Schulman Philipp Moritz Sergey Levine Michael I. Jordan Pieter Abbeel
+	Cautionary Note about<i>R</i><sup>2</sup>	1985	Tarald O. Kvålseth
+	Prioritized Experience Replay	2015	Tom Schaul John Quan Ioannis Antonoglou David Silver
+	Proximal Policy Optimization Algorithms	2017	John Schulman Filip Wolski Prafulla Dhariwal Alec Radford Oleg Klimov
+	Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation	2017	Yuhuai Wu Elman Mansimov S. Matthew Liao Roger Grosse Jimmy Ba
+	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor	2018	Tuomas Haarnoja Aurick Zhou Pieter Abbeel Sergey Levine
+	Recurrent World Models Facilitate Policy Evolution	2018	David Ha Jürgen Schmidhuber
+	Bridging the Gap Between Value and Policy Based Reinforcement Learning	2017	Ofir Nachum Mohammad Norouzi Kelvin Xu Dale Schuurmans
+	Sample Efficient Actor-Critic with Experience Replay	2016	Ziyu Wang Victor Bapst Nicolas Heess Volodymyr Mnih Rémi Munos Koray Kavukcuoglu Nando de Freitas
+	Prioritized Experience Replay	2015	Tom Schaul John Quan Ioannis Antonoglou David Silver