**arXiv ID:** 1812.11240 **Authors:** Norman Tasfi, Miriam Capretz **Published:** 2018-12-28T22:37:30Z **Abstract:** We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast ...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Dynamic Planning Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-dynamic-planning-networks)
# Dynamic Planning Networks
**arXiv ID:** 1812.11240
**Authors:** Norman Tasfi, Miriam Capretz
**Published:** 2018-12-28T22:37:30Z
**Abstract:**
We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly trial-and-error in the environment. DPN learns to efficiently form plans by expanding a single action-conditional state transition at a time instead of exhaustively evaluating each action, reducing the required number of state-transitions during planning by up to 96%. We observe various emergent planning patterns used to solve environments, including classical search methods such as breadth-first and depth-first search. DPN shows improved data efficiency, performance, and generalization to new and unseen domains in comparison to several baselines.
## Skill Description
This skill is generated from the arXiv paper: Dynamic Planning Networks (1812.11240).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1812.11240](http://arxiv.org/abs/1812.11240v2)