30 citations · 85 across the 17 of their papers we have counts for
17 papers
Bilevel MCTS for Amortized O(1) Node Selection in Classical Planning
Masataro Asai
We study an efficient implementation of Multi-Armed Bandit (MAB)-based Monte-Carlo Tree Search (MCTS) for classical planning. One weakness of MCTS is that it spends a significant t…
Extreme Value Monte Carlo Tree Search for Classical Planning
Masataro Asai, Stephen Wissow
Despite being successful in board games and reinforcement learning (RL), Monte Carlo Tree Search (MCTS) combined with Multi Armed Bandits (MABs) has seen limited success in domain-…
On Using Admissible Bounds for Learning Forward Search Heuristics
Carlos Núñez-Molina, Masataro Asai, Pablo Mesejo +1
In recent years, there has been growing interest in utilizing modern machine learning techniques to learn heuristic functions for forward search algorithms. Despite this, there has…
Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning
Stephen Wissow, Masataro Asai
Balancing exploration and exploitation has been an important problem in both game tree search and automated planning. However, while the problem has been extensively analyzed withi…
Analytical Conjugate Priors for Subclasses of Generalized Pareto Distributions
Masataro Asai
This article is written for pedagogical purposes aiming at practitioners trying to estimate the finite support of continuous probability distributions, i.e., the minimum and the ma…
Dr. Neurosymbolic, or: How I Learned to Stop Worrying and Accept Statistics
Masataro Asai
The symbolic AI community is increasingly trying to embrace machine learning in neuro-symbolic architectures, yet is still struggling due to cultural barriers. To break the barrier…
Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari
Benjamin Ayton, Masataro Asai
Width-based planning has shown promising results on Atari 2600 games using pixel input, while using substantially fewer environment interactions than reinforcement learning. Recent…
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
Clement Gehring, Masataro Asai, Rohan Chitnis +4
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 RL…
Classical Planning in Deep Latent Space
Masataro Asai, Hiroshi Kajino, Alex Fukunaga +1
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, alth…
Discrete Word Embedding for Logical Natural Language Understanding
Masataro Asai, Zilu Tang
We propose an unsupervised neural model for learning a discrete embedding of words. Unlike existing discrete embeddings, our binary embedding supports vector arithmetic operations…
Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
Masataro Asai, Christian Muise
We achieved a new milestone in the difficult task of enabling agents to learn about their environment autonomously. Our neuro-symbolic architecture is trained end-to-end to produce…
Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS
Masataro Asai
Recent work on Neural-Symbolic systems that learn the discrete planning model from images has opened a promising direction for expanding the scope of Automated Planning and Schedul…
Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
Masataro Asai, Hiroshi Kajino
While classical planning has been an active branch of AI, its applicability is limited to the tasks precisely modeled by humans. Fully automated high-level agents should be instead…
Unsupervised Grounding of Plannable First-Order Logic Representation from Images
Masataro Asai
Recently, there is an increasing interest in obtaining the relational structures of the environment in the Reinforcement Learning community. However, the resulting "relations" are…
Photo-Realistic Blocksworld Dataset
Masataro Asai
In this report, we introduce an artificial dataset generator for Photo-realistic Blocksworld domain. Blocksworld is one of the oldest high-level task planning domain that is well d…
Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions
Masataro Asai
We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. U…
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary
Masataro Asai, Alex Fukunaga
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, alth…