AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

QMDP-Net: Deep Learning for Planning under Partial Observability

Peter Karkus, David Hsu, Wee Sun Lee

NeurIPS 2017 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 27 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
Embed a Bayesian filter and QMDP planning structure rather than use QMDP aloneQMDP-net · Hallway2success rate (%): 37.3 -> 82.9Improved
Replace the structured filter with a generic LSTM filter (ablation)QMDP-net · Maze D-29success rate (%): 98.0 -> 9.8Hurt
Untie value-iteration transition weights and remove their softmax constraint (ablation)QMDP-net · Maze S-19success rate (%): 93.9 -> 98.7Mixed
Untie value-iteration transition weights and remove their softmax constraint (ablation)QMDP-net · Intel Labsuccess rate (%): 94.4 -> 20.0Hurt
Increase test-time planning iterations from K=90 to K=180 (ablation)QMDP-net trained with K=90 · Intel Labsuccess rate (%): 40.8 -> 83.4Improved
Increase test-time planning iterations from K=180 to K=450 (ablation)QMDP-net trained with K=90 · Freiburgsuccess rate (%): 93.2 -> 92.0No clear effect
Increase test-time planning iterations from K=90 to K=450 (ablation)QMDP-net trained with K=90 · Belgioiososuccess rate (%): 60.0 -> 95.4Improved
Increase test-time planning iterations from K=90 to K=450 (ablation)QMDP-net trained with K=90 · MITsuccess rate (%): 86.2 -> 91.4Improved
Increase test-time planning iterations from K=180 to K=450 (ablation)QMDP-net trained with K=90 · MITsuccess rate (%): 96.0 -> 91.4Hurt
Raise the cost of staying to 20 times its original value in the planning model (ablation)QMDP policy · Maze D-29success rate (%): 63.2 -> 65.0Improved
Raise stay cost to 50 times and turn-right cost to 10 times their original values (ablation)QMDP policy · Maze D-29success rate (%): 63.2 -> 93.0Improved
Use fixed rather than task-varying environmentsQMDP-net · Fixed gridsuccess rate (%): 98.6 vs 98.8No clear effect

Later papers that compared with this method

1 later accepted paper reports QMDP-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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