AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning

Luisa Zintgraf, Sebastian Schulze, Cong Lu, Leo Feng, Maximilian Igl, Kyriacos Shiarlis, Yarin Gal, Katja Hofmann, Shimon Whiteson

JMLR 2021 · Reinforcement learning › Visual and representation RL · approach: Task structure and curricula for meta-RL · 20 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
use variBAD instead of RL2 (best baseline)meta-RL · Meta-World ML1 Pushsuccess rate (%): 87 -> 100Improved
use variBAD instead of MAMLmeta-RL · Meta-World ML1 Reachsuccess rate (%): 48 -> 100Improved
use variBAD instead of PEARLmeta-RL · Meta-World ML1 Pick-Placesuccess rate (%): 28 -> 29No clear effect
allow second episode to adaptvariBAD · Meta-World ML1success rate (%): 100 -> 100No clear effect
add decoding of both past and future trajectory (vs past only or next step only) (ablation)variBAD VAE objective · GridWorld, AntGoal, PointRobotreturnImproved
decode full trajectory instead of future only (ablation)variBAD VAE objective · GridWorldbelief qualityImproved
use filtering KL (prior is previous posterior) instead of fixed N(0,I) prior (ablation)variBAD KL term · PointRobotreturnImproved
add KL regularisation (ablation)variBAD KL term · GridWorld, AntGoal, PointRobotreturnImproved
do not detach gradient of previous posterior in KL (ablation)variBAD KL term · GridWorld, AntGoal, PointRobotreturnImproved
increase latent dimension from 1-2 to 5 or more (ablation)variBAD · GridWorld, AntGoalnormalised performanceImproved
use very large latent (1000 GridWorld, 300 AntGoal) (ablation)variBAD · GridWorld, AntGoalnormalised performanceNo clear effect
use variBAD instead of RL2 on MuJoCometa-RL · MuJoCo (5 of 6 environments)return in first episodeImproved

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