AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Model-based Adversarial Meta-Reinforcement Learning

Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 16 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
train on adversarially chosen tasks (AdMRL) instead of uniformly sampled tasks for meta-training (ablation)model-based meta-RL (SLBO) · Ant2D 6x6 test grid, boundary taskssub-optimality gapImproved
adversarial task selection instead of Gaussian task sampling (ablation)model-based meta-RL (SLBO) · Ant2D worst-case tasksworst-case sub-optimality gapImproved
adversarial task selection instead of uniform/Gaussian sampling for high-dimensional task parameters (ablation)model-based meta-RL (SLBO) · Cheetah-Highdimworst-case sub-optimality gapImproved
adversarial task selection instead of uniform/Gaussian sampling, tested on out-of-distribution tasks (ablation)model-based meta-RL (SLBO) · Ant2D OOD tasks in [-5,5]^2sub-optimality gapImproved
adversarial task selection instead of uniform/Gaussian sampling (ablation)learned dynamics model · Ant2D OOD tasksmodel prediction L2 errorImproved
use AdMRL instead of MAML and PEARLmeta-RL on MuJoCo velocity-control tasks · Hopper2D, Walker2D, Ant2D, Ant3D, Cheetah-Highdimaverage return A_nImproved
give MAML and PEARL a multi-task policy conditioned on task parametersMAML, PEARL · MuJoCo velocity-control tasksaverage returnNo clear effect

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