DeepAI AI Chat
Log In Sign Up

Adversarial Task Transfer from Preference

by   Xiaojian Ma, et al.
Tsinghua University

Task transfer is extremely important for reinforcement learning, since it provides possibility for generalizing to new tasks. One main goal of task transfer in reinforcement learning is to transfer the action policy of an agent from the original basic task to specific target task. Existing work to address this challenging problem usually requires accurate hand-coded cost functions or rich demonstrations on the target task. This strong requirement is difficult, if not impossible, to be satisfied in many practical scenarios. In this work, we develop a novel task transfer framework which effectively performs the policy transfer using preference only. The hidden cost model for preference and adversarial training are elegantly combined to perform the task transfer. We give the theoretical analysis on the convergence about the proposed algorithm, and perform extensive simulations on some well-known examples to validate the theoretical results.


page 1

page 2

page 3

page 4


Domain Adaptation for Reinforcement Learning on the Atari

Deep reinforcement learning agents have recently been successful across ...

Adversarial Feature Training for Generalizable Robotic Visuomotor Control

Deep reinforcement learning (RL) has enabled training action-selection p...

Provable Benefits of Representational Transfer in Reinforcement Learning

We study the problem of representational transfer in RL, where an agent ...

Successor Features for Transfer in Reinforcement Learning

Transfer in reinforcement learning refers to the notion that generalizat...

Contextual Policy Reuse using Deep Mixture Models

Reinforcement learning methods that consider the context, or current sta...

Bad Citrus: Reducing Adversarial Costs with Model Distances

Recent work by Jia et al., showed the possibility of effectively computi...