IRL in General Environments

by michaelcohen1 min read10th Jul 201920 comments


Ω 6

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

Here is a proposal for Inverse Reinforcement Learning in General Environments. (2 1/2 pages; very little math).

Copying the introduction here:

The eventual aim of IRL is to understand human goals. However, typical algorithms for IRL assume the environment is finite-state Markov, and it is often left unspecified how raw observational data would be converted into a record of human actions, alongside the space of actions available. For IRL to learn human goals, the AI has to consider general environments, and it has to have a way of identifying human actions. Lest these extensions appear trivial, I consider one of the simplest proposals, and discuss some difficulties that might arise.