DeepAI AI Chat
Log In Sign Up

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

by   Zhang-Wei Hong, et al.
National Tsing Hua University
Preferred Infrastructure

Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the course of training enables faster policy improvement for an RL agent. Motivated by these recent insights, we propose Periodic Intra-Ensemble Knowledge Distillation (PIEKD). 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. Our experiments demonstrate that PIEKD improves upon a state-of-the-art RL method in sample efficiency on several challenging MuJoCo benchmark tasks. Additionally, we perform ablation studies to better understand PIEKD.


page 1

page 4

page 6


Federated Ensemble Model-based Reinforcement Learning

Federated learning (FL) is a privacy-preserving machine learning paradig...

Privileged Knowledge Distillation for Sim-to-Real Policy Generalization

Reinforcement Learning (RL) has recently achieved remarkable success in ...

KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning

Recently, deep Reinforcement Learning (RL) algorithms have achieved dram...

Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

We formally study how Ensemble of deep learning models can improve test ...

Privileged Information Dropout in Reinforcement Learning

Using privileged information during training can improve the sample effi...

Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation

In reinforcement learning, domain randomisation is an increasingly popul...