AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning via Auxillary Task Distillation

Abhinav N Harish, Larry Heck, Josiah P Hanna, Zsolt Kira, Andrew Szot

ECCV 2024 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL

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 the distillation loss from auxiliary tasks (ablation)AuxDistill · Habitat Rearrangement (Eval Unseen, all episodes)success rate (%): 0 -> 52Improved
train auxiliary and main tasks concurrently with distillation instead of a two-stage RL curriculum (ablation)AuxDistill · Habitat Rearrangement (Eval Unseen, all episodes)success rate (%): 0 -> 52Improved
include the Pick auxiliary task (ablation)AuxDistill · Rearrangement fridge subset, Evalsuccess rate (%): 0 -> 30Improved
add the Pick from Fridge auxiliary task (ablation)AuxDistill · Rearrangement fridge subset, Eval hardsuccess rate (%): 7 -> 19Improved
add the Open Fridge auxiliary task (ablation)AuxDistill · Rearrangement fridge subset, Eval all episodessuccess rate (%): 48 -> 30Hurt
increase distillation coefficient lambda from 0.1 to 1.0 (ablation)AuxDistill · Rearrangement (Eval all episodes)success rate (%): 30 -> 1Hurt
reduce distillation coefficient lambda to 0.01 (ablation)AuxDistill · Rearrangement (Eval all episodes)success rate (%): 36 -> 10Hurt
use coordinate-pick auxiliary task with distillation for Category PickAuxDistill · Category Pick (Eval Unseen)success rate (%): 9 -> 11Improved
replace pre-trained skill hierarchy (M3) with end-to-end AuxDistillHabitat rearrangement · Eval Unseen Hardsuccess rate (%): 0 -> 41Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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