AN Bajpai, S Garg - Advances in Neural Information …, 2018 - proceedings.neurips.cc
Abstract Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the …
State-of-the-art probabilistic planners typically apply look-ahead search and reasoning at each step to make a decision. While this approach can enable high-quality decisions, it can …
E Groshev, M Goldstein, A Tamar… - Proceedings of the …, 2018 - ojs.aaai.org
We present a new approach to learning for planning, where knowledge acquired while solving a given set of planning problems is used to plan faster in related, but new problem …
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex …
In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network …
In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By …
TP Bueno, LN de Barros, DD Mauá… - Proceedings of the AAAI …, 2019 - ojs.aaai.org
Recent advances in applying deep learning to planning have shown that Deep Reactive Policies (DRPs) can be powerful for fast decision-making in complex environments …
L Zhang, G Yang, BC Stadie - International conference on …, 2021 - proceedings.mlr.press
Planning, the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems, is a hallmark of human intelligence. While deep reinforcement …
Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially using graph architectures. A recent proposal, XLVIN, reaps the benefits …