AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning with Automated Auxiliary Loss Search

Tairan He, Yuge Zhang, Kan Ren, Minghuan Liu, Che Wang, Weinan Zhang, Yuqing Yang, Dongsheng Li

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 4 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 searched auxiliary loss A2-winner to SAC vs CURLSAC · DMC500K Reacher-Easy / Cheetah-Runepisodic reward: 518 -> 613Improved
add A2-winner vs CURL at 100K stepsSAC · DMC100K Reacher-Easyepisodic reward: 538 -> 778Improved
add A2-winner vs CURL at 100K stepsSAC · DMC100K Ball in cup-Catchepisodic reward: 769 -> 862Improved
add A2-winner on Atari with Efficient Rainbow vs CURLEfficient Rainbow · Atari100kmean human-normalized score: 0.381 -> 0.568Improved
add A2-winner on Atari vs DrQEfficient Rainbow · Atari100kmedian human-normalized score: 0.268 -> 0.317Improved
use a 6-layer conv encoder instead of the 4-layer encoder used in search (ablation)A2-winner · image-based DMCepisodic rewardImproved
use deeper encoder ranking 6-layer > 4-layer > 2-layer (ablation)A2-winner · image-based DMCepisodic rewardImproved
add A2-winner in 20% masked-state POMDP vs CURL and SAC-DenseMLP (ablation)SAC · Hopper-Hop and Cheetah-Run (POMDP)episodic rewardImproved
search from scratch on vector tasks (A2-winner-v) instead of reusing A2-winner (ablation)A2-winner · vector DMC 18 environmentsenvironments beating baselines: 12 -> 16Improved
MSE loss without negative samples instead of with negatives (ablation)A2LS loss operator · 3 image DMC500K envsnormalized episodic reward: 0.124 -> 1.000Improved
use 1-layer DenseMLP instead of 1-layer plain MLP encoder (ablation)A2LS · vector DMControl100Knormalized episodic reward: 0.919 -> 1.000Improved
use 4-layer instead of 1-layer DenseMLP encoder (ablation)A2LS · vector DMControl100Knormalized episodic reward: 1.000 -> 0.813Hurt

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