AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Planning in Golog

AAAI 2016 · Continual learning › Online and replay-based · approach: Plasticity-preserving continual reinforcement learning · 16 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 FF+FastDownward ensemble planner instead of FastDownward alone (ablation)GOLOG CP · Task 2, 5 cupstotal planning time (s): (183.7±1.9) s -> (0.95 ± 0.02) sHelped
use FF+FastDownward ensemble planner instead of FastDownward alone (ablation)GOLOG CP · Task 1, 2 cupstotal planning time (s): (634.5 ± 4.1) s -> (2.23 ± 0.02) sHelped
replace GKI CP (PDDL continual planner) with GOLOG continual planningcontinual planner · Task 2, 5 cupstotal planning time (s): (278.1 ± 19.9) s -> (0.95 ± 0.02) sHelped
replace GKI CP with GOLOG continual planningcontinual planner · Task 2plan quality (actions): 65.0 ± 3.4 -> 62.0±0.0No clear effect
add assertions for conditional sub-plans (ablation)GOLOG CP · Task 1, larger problemstotal planning time (s): (326.5 ± 4.9) s (6 cups, none) vs (10.0 ± 0.06) s (10 cups, with)Helped
add assertions for conditional sub-plans (ablation)GOLOG CP · Task 1, small problemstotal planning time (s)Hurt
add assertions for conditional sub-plans (ablation)GOLOG CP · Task 1, 6 cupsnumber of actions: 93.0 ± 0.0 -> 90.0 ± 0.0No clear effect

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