SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.12929 · 2018

Online Abstraction with MDP Homomorphisms for Deep Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is based on MDP homomorphisms, a structure-preserving mapping between MDPs. We demonstrate our algorithm's ability to learn abstractions from collected experience and show how to reuse the abstractions to guide exploration in new tasks the agent encounters. Our novel task transfer method outperforms baselines based on a deep Q-network in the majority of our experiments. The source code is at https://github.com/ondrejba/aamas_19.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1811.12929")
get_code_for_paper("1811.12929")
have("1811.12929")

Connect an agent — have() is free.