Timezone: »

Transfer from Multiple MDPs
Alessandro Lazaric · Marcello Restelli

Tue Dec 13 08:45 AM -- 02:59 PM (PST) @

Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include them in the training set used to solve a target task. In this paper, we investigate the theoretical properties of this transfer method and we introduce novel algorithms adapting the transfer process on the basis of the similarity between source and target tasks. Finally, we report illustrative experimental results in a continuous chain problem.

Author Information

Alessandro Lazaric (Facebook Artificial Intelligence Research)
Marcello Restelli (Politecnico di Milano)

More from the Same Authors