Provably Robust Blackbox Optimization for Reinforcement Learning

Krzysztof Choromański, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Deepali Jain, Yuxiang Yang, Atıl Işçen, Jasmine Hsu, Vikas Sindhwani

Type: Preprint

Publication Date: 2019-03-07

Citations: 7

View Publication

Locations

arXiv (Cornell University) - View

Similar Works

Action	Title	Year	Authors
+	Provably Robust Blackbox Optimization for Reinforcement Learning	2019	Krzysztof Choromański Aldo Pacchiano Jack Parker-Holder Yunhao Tang Deepali Jain Yuxiang Yang Atıl Işçen Jasmine Hsu Vikas Sindhwani
+	Wasserstein Robust Reinforcement Learning	2019	Mohammed Amin Abdullah Hang Ren Haitham Bou Ammar Vladimir Milenković Rui Luo Ming‐Tian Zhang Jun Wang
+	Action Robust Reinforcement Learning and Applications in Continuous Control	2019	Chen Tessler Yonathan Efroni Shie Mannor
+	Robust Reinforcement Learning via Adversarial training with Langevin Dynamics	2020	Parameswaran Kamalaruban Yu‐Ting Huang Ya-Ping Hsieh Paul Rolland Cheng Shi Volkan Cevher
+	Policy Gradient Bayesian Robust Optimization for Imitation Learning	2021	Zaynah Javed Daniel S. Brown Satvik Sharma Junwei Zhu Ashwin Balakrishna Marek Petrik Anca D. Dragan Ken Goldberg
+ PDF Chat	Black-box data-efficient policy search for robotics	2017	Konstantinos Chatzilygeroudis Roberto Rama Rituraj Kaushik Dorian Goepp Vassilis Vassiliades Jean-Baptiste Mouret
+	Black-Box Data-efficient Policy Search for Robotics	2017	Konstantinos Chatzilygeroudis Roberto Rama Rituraj Kaushik Dorian Goepp Vassilis Vassiliades Jean-Baptiste Mouret
+	Black-Box Data-efficient Policy Search for Robotics	2017	Konstantinos Chatzilygeroudis Roberto Rama Rituraj Kaushik Dorian Goepp Vassilis Vassiliades Jean-Baptiste Mouret
+	Overcoming Model Bias for Robust Offline Deep Reinforcement Learning	2020	Phillip Swazinna Steffen Udluft Thomas A. Runkler
+	Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control	2022	Maximilian Hüttenrauch Gerhard Neumann
+	Overcoming Model Bias for Robust Offline Deep Reinforcement Learning.	2020	Phillip Swazinna Steffen Udluft Thomas A. Runkler
+	Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula	2023	Aryaman Reddi Maximilian Tölle Jan Peters Georgia Chalvatzaki Carlo D’Eramo
+	Soft Actor-Critic Algorithms and Applications	2018	Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel
+	Provably Convergent Policy Optimization via Metric-aware Trust Region Methods	2023	Jun Ho Song Niao He Lijun Ding Chaoyue Zhao
+ PDF Chat	Proximal Reliability Optimization for Reinforcement Learning	2020	Narendra Patwardhan
+	Robust Reinforcement Learning for Continuous Control with Model Misspecification	2020	Daniel J. Mankowitz Nir Levine Rae Jeong Abbas Abdolmaleki Jost Tobias Springenberg Yuanyuan Shi Jackie Kay Todd Hester Timothy Mann Martin Riedmiller
+	Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations	2022	Sean Gillen Katie Byl
+	Proximal Reliability Optimization for Reinforcement Learning	2019	Narendra Patwardhan Zequn Wang
+	Robust Reinforcement Learning for Continuous Control with Model Misspecification	2019	Daniel J. Mankowitz Nir Levine Rae Jeong Yuanyuan Shi Jackie Kay Abbas Abdolmaleki Jost Tobias Springenberg Timothy Mann Todd Hester Martin Riedmiller
+	Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking	2022	Hanna Krasowski Jakob Thumm Marlon Müller Xiao Wang Matthias Althoff

Works That Cite This (6)

Action	Title	Year	Authors
+	Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes	2019	Krzysztof Choromański Aldo Pacchiano Jack Parker-Holder Yunhao Tang
+ PDF Chat	Accelerating reinforcement learning with a Directional-Gaussian-Smoothing evolution strategy	2021	Jiaxin Zhang Hoang Tran Guannan Zhang
+	A Scalable Evolution Strategy with Directional Gaussian Smoothing for Blackbox Optimization.	2020	Jiaxin Zhang Hoang Tran Dan Lu Guannan Zhang
+	Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy	2020	Jiaxing Zhang Hoang Tran Guannan Zhang
+	CoNES: Convex Natural Evolutionary Strategies	2020	Sushant Veer Anirudha Majumdar
+	qiBullet, a Bullet-based simulator for the Pepper and NAO robots.	2019	Maxime Busy Maxime Caniot

Works Cited by This (16)

Action	Title	Year	Authors
+	Introduction to Derivative-Free Optimization	2009	Andrew R. Conn Katya Scheinberg L. N. Vicente
+ PDF Chat	Decoding by Linear Programming	2005	Emmanuel J. Candès Terence Tao
+	Random Gradient-Free Minimization of Convex Functions	2015	Yurii Nesterov Vladimir Spokoiny
+ PDF Chat	Optimization by Direct Search: New Perspectives on Some Classical and Modern Methods	2003	Tamara G. Kolda Robert Michael Lewis Virginia Torczon
+	Continuous control with deep reinforcement learning	2015	Timothy Lillicrap Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver Daan Wierstra
+ PDF Chat	Introduction to Online Convex Optimization	2016	Elad Hazan
+	Sharper Bounds for Regression and Low-Rank Approximation with Regularization.	2016	Haim Avron Kenneth L. Clarkson David P. Woodruff
+	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	2017	Tim Salimans Jonathan Ho Xi Chen Ilya Sutskever
+	Proximal Policy Optimization Algorithms	2017	John Schulman Filip Wolski Prafulla Dhariwal Alec Radford Oleg Klimov
+	Simple random search provides a competitive approach to reinforcement learning	2018	Horia Mania Aurelia Guy Benjamin Recht