`

Timezone: »

 
Poster
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
Michael Dennis · Natasha Jaques · Eugene Vinitsky · Alexandre Bayen · Stuart Russell · Andrew Critch · Sergey Levine

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #156
in Poster Session 1 »

A wide range of reinforcement learning (RL) problems --- including robustness, transfer learning, unsupervised RL, and emergent complexity --- require specifying a distribution of tasks or environments in which a policy will be trained. However, creating a useful distribution of environments is error prone, and takes a significant amount of developer time and effort. We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. Existing approaches to automatically generating environments suffer from common failure modes: domain randomization cannot generate structure or adapt the difficulty of the environment to the agent's learning progress, and minimax adversarial training leads to worst-case environments that are often unsolvable. To generate structured, solvable environments for our protagonist agent, we introduce a second, antagonist agent that is allied with the environment-generating adversary. The adversary is motivated to generate environments which maximize regret, defined as the difference between the protagonist and antagonist agent's return. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED). Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.

Author Information

Michael Dennis (University of California Berkeley)

Michael Dennis is a 5th year grad student at the Center for Human-Compatible AI. With a background in theoretical computer science, he is working to close the gap between decision theoretic and game theoretic recommendations and the current state of the art approaches to robust RL and multi-agent RL. The overall aim of this work is to ensure that our systems behave in a way that is robustly beneficial. In the single agent setting, this means making decisions and managing risk in the way the designer intends. In the multi-agent setting, this means ensuring that the concerns of the designer and those of others in the society are fairly and justly negotiated to the benefit of all involved.

Natasha Jaques (Google Brain, UC Berkeley)
Eugene Vinitsky (UC Berkeley)
Alexandre Bayen (UC Berkeley)
Stuart Russell (UC Berkeley)
Andrew Critch (UC Berkeley)
Sergey Levine (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors