AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Matthew Thomas Jackson, Minqi Jiang, Jack Parker-Holder, Risto Vuorio, Chris Lu, Gregory Farquhar, Shimon Whiteson, Jakob Nicolaus Foerster

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Task-inference meta-RL · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adversarial environment design (GROOVE) to LPG meta-trainingLPG · unseen Grid-Worldsfraction of tasks below 75% A2C-normalized return: 187% more tasks fail for LPGImproved
add environment design to LPGLPG · Grid-World higher-scoring half of tasksnormalized returnNo clear effect
add environment design to LPGLPG · Ataritasks with higher mean score: 17 -> 39Improved
add environment design to LPGLPG · Atari (IQM and optimality gap)aggregate performanceImproved
use algorithmic regret instead of uniform scoring (domain randomization) (ablation)GROOVE · Min-AtarreturnImproved
use algorithmic regret instead of optimal-policy regret (ablation)GROOVE · Min-AtarreturnImproved
use L1 value loss or positive value loss instead of uniform scoring (ablation)GROOVE · Min-AtarreturnNo clear effect
use positive value loss instead of uniform scoring (ablation)GROOVE · Min-AtarreturnHurt
use A2C or PPO antagonist instead of random or expert agent in AR (ablation)GROOVE · Min-AtarreturnImproved
use A2C antagonist instead of PPO in AR (ablation)GROOVE · Min-AtarreturnImproved
increase number of random training levels (ablation)LPG · Min-AtarreturnImproved
train on handcrafted instead of random levels (same count) (ablation)LPG · Min-AtarreturnMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy