REVIEW 2 cited by
Generalized Planning With Deep Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
A hallmark of intelligence is the ability to deduce general principles from examples, which are correct beyond the range of those observed. Generalized Planning deals with finding such principles for a class of planning problems, so that principles discovered using small instances of a domain can be used to solve much larger instances of the same domain. In this work we study the use of Deep Reinforcement Learning and Graph Neural Networks to learn such generalized policies and demonstrate that they can generalize to instances that are orders of magnitude larger than those they were trained on.
Forward citations
Cited by 2 Pith papers
-
Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
Dynamically generating larger validation instances during training selects planning policies that generalize to larger instances better than fixed validation sets, across all 9 domains tested.
-
Relational GNNs Cannot Learn $C_2$ Features for Planning
Relational GNNs cannot represent C2 logic features for planning value functions, as shown by an indistinguishability counterexample and experiments, while PLOI-style graph encodings can.
Discussion (0). Continue with ORCID to comment.