AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Learning Partial Policies to Speedup MDP Tree Search via Reduction to I.I.D. Learning

Jervis Pinto, Alan Fern

JMLR 2017 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 7 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 Q-cost (regret-based) loss instead of zero-one cost for partial policy learning (FT-QCM vs FT-OPI) (ablation)UCT with learned partial policy · Galcon and Yahtzeeaverage episodic rewardImproved
add forward training to OPI (FT-OPI vs OPI) (ablation)UCT with learned partial policy · Galcon and Yahtzeeaverage episodic rewardNo clear effect
use FT-QCM instead of OPI/FT-OPI at low pruning threshold (ablation)UCT with learned partial policy · Galcon (sigma_d = 0.5)average episodic rewardNo clear effect
use FT-QCM at reduced 50% pruning (ablation)UCT with learned partial policy · Yahtzee (sigma_d = 0.5)average episodic rewardImproved
use FT-QCM instead of FT-OPI and OPI (ablation)partial policy pruning · held-out states, Galcon and Yahtzee rootaverage regretImproved
use FT-QCM instead of FT-OPI and OPI (ablation)partial policy pruning · held-out states, Galcon and Yahtzee rootpruning errorImproved
go deeper in the tree (depth d>0) for learned policiesFT-QCM · GalconregretHurt
go deeper in the tree (depth d>0) for learned policiesFT-QCM · YahtzeeregretNo clear effect
prune too many actions (large sigma_d)UCT with partial policy · Galcon and Yahtzeesearch performanceHurt
prune too few actionsUCT with partial policy · Galcon and Yahtzeesearch performanceHurt
use FT-QCM pruning with small search budgetUCT(FT-QCM) · Galcon and Yahtzeeaverage episodic rewardImproved

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