AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition

Suyoung Lee, Myungsik Cho, Youngchul Sung

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Task structure and curricula for meta-RL · 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
Add subtask decomposition and virtual training (SDVT) to LDMLDM · Meta-World ML-10 testsuccess rate (%): 19.8 -> 32.8Improved
Replace VariBAD with SDVTVariBAD · Meta-World ML-10 testsuccess rate (%): 14.1 -> 32.8Improved
Replace LDM with SDVTLDM · Meta-World ML-45 testsuccess rate (%): 24.8 -> 28.1Improved
Replace single Gaussian latent with Gaussian mixture subtask decomposition (SD)VariBAD · Meta-World ML-45 trainsuccess rate (%): 57.0 -> 61.0Improved
Add virtual training and dispersion to SD (ablation)SD · Meta-World ML-10 testsuccess rate (%): 30.8 -> 32.8Improved
Add virtual training and dispersion to SD (ablation)SD · Meta-World ML-45 testsuccess rate (%): 23.0 -> 28.1Improved
Use lightweight version (K=5, no occupancy regularization) instead of K=Ntrain (ablation)SDVT · Meta-World ML-10 trainsuccess rate (%): 77.2 -> 62.1Hurt
Use lightweight version (K=5) instead of K=Ntrain (ablation)SDVT · Meta-World ML-45 testsuccess rate (%): 28.1 -> 31.2Improved
Use lightweight version (K=5) instead of K=Ntrain (ablation)SDVT · Meta-World ML-10 testsuccess rate (%): 32.8 -> 33.4No clear effect
Use lightweight version (K=5) instead of K=Ntrain (ablation)SDVT · Meta-World ML-10 testreturn: 1225 -> 1527Improved
Use lightweight version for SD (SD-LW instead of SD) (ablation)SD · Meta-World ML-10 testsuccess rate (%): 30.8 -> 26.2Hurt
Vary categorical coefficient alphac (0.1 or 2.0 instead of 0.5) in SDVT-LW (ablation)SDVT-LW · Meta-World ML-10subtask decomposition qualityHurt

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