Feb 1, 2020 · 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.

Sep 10, 2021 · 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.

This is official implementation of an under-review conference paper titled "Periodic intra-ensemble Knowledge Distillation for Reinforcement Learning".

Nov 21, 2024 · PIEKD is a learning framework that uses an ensemble of policies to act in the environment while periodically sharing knowledge amongst policies ...

Feb 1, 2020 · PIEKD is a learning framework that uses an ensemble of policies to act in the environment while periodically sharing knowledge amongst ...

Feb 1, 2020 · This paper's primary contribution is Periodic Intra-. Ensemble Knowledge Distillation (PIEKD), a simple yet ef- fective framework for off-policy ...

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning Zhang-Wei Hong, Prabhat Nagarajan, and Guilherme J. Maeda

Research: My research focuses on advancing reinforcement learning (RL) methods to overcome the challenges of applying RL to computational discovery problems.

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 ...

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning. ZW Hong, P Nagarajan, G Maeda. European Conference on Machine Learning and Principles ...