Siddharth Mysore

2 accepted papers

2022

Multi-Critic Actor Learning: Teaching RL Policies to Act with Style

Siddharth Mysore, George Cheng, Yunqi Zhao, Kate Saenko, Meng Wu

ICLR 2022poster

Using a single value function (critic) shared over multiple tasks in Actor-Critic multi-task reinforcement learning (MTRL) can result in negative interference between tasks, which can compromise learning performance. Multi-Critic Actor Learning (MultiCriticAL) proposes instead maintaining separate c…

Cited by 32 Source ↗PDF ↗Scholar ↗

2021

Regularizing Action Policies for Smooth Control with Reinforcement Learning

Siddharth Mysore, Bassel Mabsout, Renato Mancuso, Kate Saenko

ICRA 2021poster

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. This trend often presents itself in the form of control signal oscillation and can result in poor control, high powe…

Cited by 106 Source ↗Scholar ↗