SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.07716 · AAAI · 2021

How RL Agents Behave When Their Actions Are Modified

Tom Everitt, Eric Langlois

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. The repositories linked to it are 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

Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. As a result of supervisor intervention, the executed action may differ from the action specified by the policy. How does this affect learning? We present the Modified-Action Markov Decision Process, an extension of the MDP model that allows actions to differ from the policy. We analyze the asymptotic behaviours of common reinforcement learning algorithms in this setting and show that they adapt in different ways: some completely ignore modifications while others go to various lengths in trying to avoid action modifications that decrease reward. By choosing the right algorithm, developers can prevent their agents from learning to circumvent interruptions or constraints, and better control agent responses to other kinds of action modification, like self-damage.

For agents

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

get_harvested_code_for_paper("2102.07716")
get_code_for_paper("2102.07716")
have("2102.07716")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.07716.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.07716.svg)](https://syntology.ai/paper/2102.07716)

Connect an agent — have() is free.