Timothy A. Mann

57 papers A* 18A 3Misc 1Journal 29Unranked 6

Year	Rank	Type	Title / Venue / Authors
2022	A*	`conf`	Defending Against Image Corruptions Through Adversarial Augmentations. ICLR Dan Andrei Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, András György, Timothy A. Mann, Sven Gowal
2022	J	`jnl`	MuZero with Self-competition for Rate Control in VP9 Video Compression. CoRR Amol Mandhane, Anton Zhernov, Maribeth Rauh, Chenjie Gu, Miaosen Wang, Flora Xue, Wendy Shang, Derek Pang, Rene Claus, Ching-Han Chiang, Cheng Chen, Jingning Han, Angie Chen, Daniel J. Mankowitz, Jackson Broshear, Julian Schrittwieser, Thomas Hubert, Oriol Vinyals, Timothy A. Mann
2021	A*	`conf`	Balancing Constraints and Rewards with Meta-Gradient D4PG. ICLR Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy A. Mann
2021	A*	`conf`	Data Augmentation Can Improve Robustness. NeurIPS Sylvestre-Alvise Rebuffi, Sven Gowal, Dan Andrei Calian, Florian Stimberg, Olivia Wiles, Timothy A. Mann
2021	J	`jnl`	Data Augmentation Can Improve Robustness. CoRR Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy A. Mann
2021	J	`jnl`	Defending Against Image Corruptions Through Adversarial Augmentations. CoRR Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, András György, Timothy A. Mann, Sven Gowal
2021	J	`jnl`	Fixing Data Augmentation to Improve Adversarial Robustness. CoRR Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy A. Mann
2021	A*	`conf`	Improving Robustness using Generated Data. NeurIPS Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy A. Mann
2021	J	`jnl`	Improving Robustness using Generated Data. CoRR Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy A. Mann
2021	A*	`conf`	Self-supervised Adversarial Robustness for the Low-label, High-data Regime. ICLR Sven Gowal, Po-Sen Huang, Aäron van den Oord, Timothy A. Mann, Pushmeet Kohli
2020	A*	`conf`	Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations. CVPR Sven Gowal, Chongli Qin, Po-Sen Huang, A. Taylan Cemgil, Krishnamurthy Dvijotham, Timothy A. Mann, Pushmeet Kohli
2020	J	`jnl`	Balancing Constraints and Rewards with Meta-Gradient D4PG. CoRR Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy A. Mann
2020	J	`jnl`	Non-Stationary Bandits with Intermediate Observations. CoRR Claire Vernade, András György, Timothy A. Mann
2020	A*	`conf`	Non-Stationary Delayed Bandits with Intermediate Observations. ICML Claire Vernade, András György, Timothy A. Mann
2020	J	`jnl`	Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification. CoRR Daniel J. Mankowitz, Dan A. Calian, Rae Jeong, Cosmin Paduraru, Nicolas Heess, Sumanth Dathathri, Martin A. Riedmiller, Timothy A. Mann
2020	A*	`conf`	Robust Reinforcement Learning for Continuous Control with Model Misspecification. ICLR Daniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg, Yuanyuan Shi, Jackie Kay, Todd Hester, Timothy A. Mann, Martin A. Riedmiller
2020	A*	`conf`	The NodeHopper: Enabling Low Latency Ranking with Constraints via a Fast Dual Solver. KDD Anton Zhernov, Krishnamurthy (Dj) Dvijotham, Ivan Lobov, Dan A. Calian, Michelle X. Gong, Natarajan Chandrashekar, Timothy A. Mann
2020	J	`jnl`	Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples. CoRR Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy A. Mann, Pushmeet Kohli
2019	A	`conf`	A Bayesian Approach to Robust Reinforcement Learning. UAI Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2019	J	`jnl`	A Bayesian Approach to Robust Reinforcement Learning. CoRR Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2019	A*	`conf`	A Dual Approach to Verify and Train Deep Networks. IJCAI Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Timothy A. Mann, Pushmeet Kohli
2019	J	`jnl`	Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations. CoRR Sven Gowal, Chongli Qin, Po-Sen Huang, A. Taylan Cemgil, Krishnamurthy Dvijotham, Timothy A. Mann, Pushmeet Kohli
2019	A*	`conf`	Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. NeurIPS Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto, Gergely Neu
2019	J	`jnl`	Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. CoRR Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy A. Mann, André Barreto, Sylvain Gelly, Gergely Neu
2019	J	`jnl`	An Alternative Surrogate Loss for PGD-based Adversarial Testing. CoRR Sven Gowal, Jonathan Uesato, Chongli Qin, Po-Sen Huang, Timothy A. Mann, Pushmeet Kohli
2019	—	`conf`	Beyond Greedy Ranking: Slate Optimization via List-CVAE. ICLR (Poster) Ray Jiang, Sven Gowal, Yuqiu Qian, Timothy A. Mann, Danilo J. Rezende
2019	A*	`conf`	Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems. ICML Timothy A. Mann, Sven Gowal, András György, Huiyi Hu, Ray Jiang, Balaji Lakshminarayanan, Prav Srinivasan
2019	J	`jnl`	Robust Reinforcement Learning for Continuous Control with Model Misspecification. CoRR Daniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg, Timothy A. Mann, Todd Hester, Martin A. Riedmiller
2018	A	`conf`	A Dual Approach to Scalable Verification of Deep Networks. UAI Krishnamurthy Dvijotham, Robert Stanforth, Sven Gowal, Timothy A. Mann, Pushmeet Kohli
2018	J	`jnl`	A Dual Approach to Scalable Verification of Deep Networks. CoRR Krishnamurthy Dvijotham, Robert Stanforth, Sven Gowal, Timothy A. Mann, Pushmeet Kohli
2018	A*	`conf`	Learning Robust Options. AAAI Daniel J. Mankowitz, Timothy A. Mann, Pierre-Luc Bacon, Doina Precup, Shie Mannor
2018	J	`jnl`	Learning Robust Options. CoRR Daniel J. Mankowitz, Timothy A. Mann, Pierre-Luc Bacon, Doina Precup, Shie Mannor
2018	J	`jnl`	Learning from Delayed Outcomes with Intermediate Observations. CoRR Timothy A. Mann, Sven Gowal, Ray Jiang, Huiyi Hu, Balaji Lakshminarayanan, András György
2018	J	`jnl`	On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models. CoRR Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy A. Mann, Pushmeet Kohli
2018	J	`jnl`	Optimizing Slate Recommendations via Slate-CVAE. CoRR Ray Jiang, Sven Gowal, Timothy A. Mann, Danilo J. Rezende
2018	A	`conf`	Soft-Robust Actor-Critic Policy-Gradient. UAI Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2018	J	`jnl`	Soft-Robust Actor-Critic Policy-Gradient. CoRR Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2018	J	`jnl`	Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem. CoRR Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto
2017	A*	`conf`	Approximate Value Iteration with Temporally Extended Actions (Extended Abstract). IJCAI Timothy A. Mann, Shie Mannor, Doina Precup
2016	J	`jnl`	Adaptive Lambda Least-Squares Temporal Difference Learning. CoRR Timothy A. Mann, Hugo Penedones, Shie Mannor, Todd Hester
2016	—	`conf`	Adaptive Skills Adaptive Partitions (ASAP). NIPS Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2016	J	`jnl`	Adaptive Skills, Adaptive Partitions (ASAP). CoRR Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2016	J	`jnl`	Iterative Hierarchical Optimization for Misspecified Problems (IHOMP). CoRR Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2015	J	`jnl`	Actively Learning to Attract Followers on Twitter. CoRR Nir Levine, Timothy A. Mann, Shie Mannor
2015	J	`jnl`	Approximate Value Iteration with Temporally Extended Actions. J. Artif. Intell. Res. Timothy A. Mann, Shie Mannor, Doina Precup
2015	J	`jnl`	Bootstrapping Skills. CoRR Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
2015	—	`conf`	Learning When to Switch between Skills in a High Dimensional Domain. AAAI Workshop: Learning for General Competency in Video Games Timothy A. Mann, Daniel J. Mankowitz, Shie Mannor
2015	A*	`conf`	Off-policy Model-based Learning under Unknown Factored Dynamics. ICML Assaf Hallak, François Schnitzler, Timothy A. Mann, Shie Mannor
2015	J	`jnl`	Off-policy evaluation for MDPs with unknown structure. CoRR Assaf Hallak, François Schnitzler, Timothy A. Mann, Shie Mannor
2014	—	`conf`	How hard is my MDP?" The distribution-norm to the rescue". NIPS Odalric-Ambrym Maillard, Timothy A. Mann, Shie Mannor
2014	A*	`conf`	Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations. ICML Timothy A. Mann, Shie Mannor
2014	A*	`conf`	Time-Regularized Interrupting Options (TRIO). ICML Timothy A. Mann, Daniel J. Mankowitz, Shie Mannor
2013	J	`jnl`	Autonomous and Interactive Improvement of Binocular Visual Depth Estimation through Sensorimotor Interaction. IEEE Trans. Auton. Ment. Dev. Timothy A. Mann, Yunjung Park, Sungmoon Jeong, Minho Lee, Yoonsuck Choe
2012	—	`conf`	Directed Exploration in Reinforcement Learning with Transferred Knowledge. EWRL Timothy A. Mann, Yoonsuck Choe
2011	A*	`conf`	Scaling Up Reinforcement Learning through Targeted Exploration. AAAI Timothy A. Mann, Yoonsuck Choe
2010	—	`conf`	Prenatal to postnatal transfer of motor skills through motor-compatible sensory representations. ICDL Timothy A. Mann, Yoonsuck Choe
2008	Misc	`conf`	Effects of Varying the Delay Distribution in Random, Scale-free, and Small-world Networks. GrC Bum Soon Jang, Timothy A. Mann, Yoonsuck Choe