Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

1 code implementation • 1 Feb 2020 • Zhang-Wei Hong, Prabhat Nagarajan, Guilherme Maeda

PIEKD is a learning framework that uses an ensemble of policies to act in the environment while periodically sharing knowledge amongst policies in the ensemble through knowledge distillation.

Knowledge Distillation reinforcement-learning +1

Phase Portraits as Movement Primitives for Fast Humanoid Robot Control

no code implementations • 7 Dec 2019 • Guilherme Maeda, Okan Koc, Jun Morimoto

This natural sense to infer temporal dynamics and coordination motivates us to approach robot control from a motor skill learning perspective to design fast and computationally light controllers that can be learned autonomously by the robot under mild modeling assumptions.

Collaborative Inter-agent Knowledge Distillation for Reinforcement Learning

no code implementations • 25 Sep 2019 • Zhang-Wei Hong, Prabhat Nagarajan, Guilherme Maeda

Reinforcement Learning (RL) has demonstrated promising results across several sequential decision-making tasks.

Decision Making Knowledge Distillation +2