AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Structure Learning-Based Task Decomposition for Reinforcement Learning in Non-stationary Environments

Honguk Woo, Gwangpyo Yoo, Minjong Yoo

AAAI 2022 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 2 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 TDE+OGD instead of LILACRL in 2D navigation and Minitaur · 2D navigation and Minitauraverage episodic reward: 46.4%Improved
Use TDE+OGD instead of LILACAirsim drone flying · Airsim-based drone flyingaverage episodic reward: 67.4%Improved
Add CycleGAN-based task decomposition to the auto-encoder variant (ablation)TDE+OGD · 2D navigation, low task uncertaintyepisodic reward: 6.2%Improved
Add CycleGAN-based task decomposition to the auto-encoder variant (ablation)TDE+OGD · 2D navigation, medium and high task uncertaintyepisodic reward: 14.4% (mid) and 18.6% (high)Improved
Add OGD to TDE (ablation)TDE+OGD · 2D navigation, medium and high task uncertaintyepisodic reward: 8.3% (mid) and 10.1% (high)Improved
Use TDE+OGD rather than TDE or TE+OGD (ablation)RL in 2D navigation · 2D navigation, high task uncertaintyepisodic reward: 14.4% (mid) and 18.6% (high); 8.3% (mid) and 10.1% (high)Improved
Increase task uncertainty from low to highTDE+OGD · 2D navigationepisodic reward: 17.3%Hurt
Increase task uncertainty from low to highLILAC · 2D navigationepisodic reward: 62.1%Hurt
Increase task uncertainty from low to highTDE+OGD · Airsim-based drone flyingepisodic reward: 8.6%Hurt
Increase task uncertainty from low to highLILAC · Airsim-based drone flyingepisodic reward: 12.28%Hurt

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