SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1711.09883 · 2017

AI Safety Gridworlds

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

We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration, as well as robustness to self-modification, distributional shift, and adversaries. To measure compliance with the intended safe behavior, we equip each environment with a performance function that is hidden from the agent. This allows us to categorize AI safety problems into robustness and specification problems, depending on whether the performance function corresponds to the observed reward function. We evaluate A2C and Rainbow, two recent deep reinforcement learning agents, on our environments and show that they are not able to solve them satisfactorily.

For agents

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

get_harvested_code_for_paper("1711.09883")
get_code_for_paper("1711.09883")
have("1711.09883")

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

curl https://syntology.ai/api/ran/1711.09883.json

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

[![Syntology run record](https://syntology.ai/api/ran/1711.09883.svg)](https://syntology.ai/paper/1711.09883)

Connect an agent — have() is free.