pith. sign in

arxiv: 1812.11240 · v2 · pith:U4XDZQNHnew · submitted 2018-12-28 · 💻 cs.LG · cs.AI· cs.NE· stat.ML

Dynamic Planning Networks

classification 💻 cs.LG cs.AIcs.NEstat.ML
keywords planningactionarchitecturedynamicefficientlylearnsmethodsmodel-based
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.