HyperPPO: A scalable method for finding small policies for robotic control

no code implementations • 28 Sep 2023 • Shashank Hegde, Zhehui Huang, Gaurav S. Sukhatme

We demonstrate that the neural policies estimated by HyperPPO are capable of decentralized control of a Crazyflie2. 1 quadrotor.

Efficiently Learning Small Policies for Locomotion and Manipulation

no code implementations • 30 Sep 2022 • Shashank Hegde, Gaurav S. Sukhatme

Neural control of memory-constrained, agile robots requires small, yet highly performant models.

reinforcement-learning Reinforcement Learning (RL)

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems

1 code implementation • 5 Jul 2021 • Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko

We are currently in the process of merging the augmented simulator with the main ViZDoom code repository.

Game of Doom reinforcement-learning +2