1 code implementation • 17 Jan 2023 • Bassel El Mabsout, Shahin Roozkhosh, Siddharth Mysore, Kate Saenko, Renato Mancuso
And (iii) anchor critics to help stabilize the fine-tuning of agents during sim-to-real transfer, online learning from real data while retaining behavior optimized in simulation.
no code implementations • 7 Oct 2021 • Aldair E. Gongora, Siddharth Mysore, Beichen Li, Wan Shou, Wojciech Matusik, Elise F. Morgan, Keith A. Brown, Emily Whiting
Advancements in additive manufacturing have enabled design and fabrication of materials and structures not previously realizable.
no code implementations • ICLR 2022 • Siddharth Mysore, George Cheng, Yunqi Zhao, Kate Saenko, Meng Wu
MultiCriticAL is tested in the context of multi-style learning, a special case of MTRL where agents are trained to behave with different distinct behavior styles, and yields up to 45% performance gains over the single-critic baselines and even successfully learns behavior styles in cases where single-critic approaches may simply fail to learn.
no code implementations • 23 Feb 2021 • Siddharth Mysore, Bassel Mabsout, Renato Mancuso, Kate Saenko
Actors and critics in actor-critic reinforcement learning algorithms are functionally separate, yet they often use the same network architectures.
no code implementations • 11 Dec 2020 • Siddharth Mysore, Bassel Mabsout, Renato Mancuso, Kate Saenko
A critical problem with the practical utility of controllers trained with deep Reinforcement Learning (RL) is the notable lack of smoothness in the actions learned by the RL policies.
no code implementations • 27 Sep 2018 • Siddharth Mysore, Robert Platt, Kate Saenko
We propose a novel method to exploit this observation to develop robust actor policies, by automatically developing a sampling curriculum over environment settings to use in training.