DeepAI AI Chat
Log In Sign Up

Time-Variant Variational Transfer for Value Functions

by   Giuseppe Canonaco, et al.

In most transfer learning approaches to reinforcement learning (RL) the distribution over the tasks is assumed to be stationary. Therefore, the target and source tasks are i.i.d. samples of the same distribution. In the context of this work, we will consider the problem of transferring value functions through a variational method when the distribution generating the tasks is time-variant, proposing a solution leveraging this temporal structure inherent to the task generating process. Moreover, by means of a finite sample analysis, the previously mentioned solution will be theoretically compared to its time-invariant version. Finally, we will provide an experimental evaluation of the proposed technique with three distinct time dynamics in three different RL environments.


page 1

page 2

page 3

page 4


Importance Weighted Transfer of Samples in Reinforcement Learning

We consider the transfer of experience samples (i.e., tuples < s, a, s',...

Transfer Learning in Deep Reinforcement Learning: A Survey

This paper surveys the field of transfer learning in the problem setting...

Transfer from Multiple MDPs

Transfer reinforcement learning (RL) methods leverage on the experience ...

Target Transfer Q-Learning and Its Convergence Analysis

Q-learning is one of the most popular methods in Reinforcement Learning ...

Transfer of Temporal Logic Formulas in Reinforcement Learning

Transferring high-level knowledge from a source task to a target task is...

A New Representation of Successor Features for Transfer across Dissimilar Environments

Transfer in reinforcement learning is usually achieved through generalis...

Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity

Transfer learning methods for reinforcement learning (RL) domains facili...