Reward learning from human preferences and demonstrations in Atari Reward learning from human preferences and demonstrations in Atari
Paper summary How can humans help an agent perform at a task that has no clear reward? Imitation, demonstration, and preferences. This paper asks which combinations of imitation, demonstration, and preferences will best guide an agent in Atari games. For example an agent that is playing Pong on the Atari, but can't access the score. You might help it by demonstrating your play style for a few hours. To help the agent further you are shown two short clips of it playing and you are asked to indicate which one, if any, you prefer. To avoid spending many hours rating videos the authors sometimes used an automated approach where the game's score decides which clip is preferred, but they also compared this approach to human preferences. It turns out that human preferences are often worse because of reward traps. These happen, for example, when the human tries to encourage the agent to explore ladders, resulting in the agent obsessing about ladders instead of continuing the game. They also observed that the agent often misunderstood the preferences it was given, causing unexpected behavior called reward hacking. The only solution they mention was to have someone keep an eye on it and continue giving it preferences, but this isn't always feasible. This is the alignment problem which is a hard problem in AGI research. Results: adding merely a few thousand preferences can help in most games, unless they have sparse rewards. Demonstrations, on the other hand, tend to help those games with sparse rewards but only if the demonstrator is good at the game.
arxiv.org
arxiv-sanity.com
scholar.google.com
Reward learning from human preferences and demonstrations in Atari
Borja Ibarz and Jan Leike and Tobias Pohlen and Geoffrey Irving and Shane Legg and Dario Amodei
arXiv e-Print archive - 2018 via Local arXiv
Keywords: cs.LG, cs.AI, cs.NE, stat.ML

more

Summary by wassname 3 weeks ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and