Search Results for author:
Found 17 papers, 6 papers with code
Likelihood-based Permutation Invariant Loss Function for Probability Distributions
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.
On Using Admissible Bounds for Learning Forward Search Heuristics
This results in a different loss function from the MSE commonly employed in the literature, which implicitly models the learned heuristic as a gaussian distribution.
Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning
However, while the problem has been extensively analyzed within the Multi-Armed Bandit (MAB) literature, the planning community has had limited success when attempting to apply those results.
Analytical Conjugate Priors for Subclasses of Generalized Pareto Distributions
Moreover, existing literature focuses on estimating the scale {\sigma} and the shape {\xi}, lacking discussion of the estimation of the location {\theta} which is the lower support of (minimum value possible in) a GP.
Dr. Neurosymbolic, or: How I Learned to Stop Worrying and Accept Statistics
It provides a step-by-step protocol for designing a machine learning system that satisfies a minimum theoretical guarantee necessary for being taken seriously by the symbolic AI community, i. e., it discusses "in what condition we can stop worrying and accept statistical machine learning."
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
In this paper, we propose to leverage domain-independent heuristic functions commonly used in the classical planning literature to improve the sample efficiency of RL.
Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari
Width-based planning has shown promising results on Atari 2600 games using pixel input, while using substantially fewer environment interactions than reinforcement learning.
Classical Planning in Deep Latent Space
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck.
Generating Plannable Lifted Action Models for Visually Generated Logical Predicates
We propose FOSAE++, an unsupervised end-to-end neural system that generates a compact discrete state transition model (dynamics / action model) from raw visual observations.
Discrete Word Embedding for Logical Natural Language Understanding
We propose an unsupervised neural model for learning a discrete embedding of words.
Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
We achieved a new milestone in the difficult task of enabling agents to learn about their environment autonomously.
Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS
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 Scheduling to the raw, noisy data.
Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
We analyze the problem in Latplan both formally and empirically, and propose "Zero-Suppressed SAE", an enhancement that stabilizes the propositions using the idea of closed-world assumption as a prior for NN optimization.
Unsupervised Grounding of Plannable First-Order Logic Representation from Images
In the experiment using 8-Puzzle and a photo-realistic Blocksworld environment, we show that (1) the resulting predicates capture the interpretable relations (e. g. spatial), (2) they help obtaining the compact, abstract model of the environment, and finally, (3) the resulting model is compatible to symbolic classical planning.
Photo-Realistic Blocksworld Dataset
In this report, we introduce an artificial dataset generator for Photo-realistic Blocksworld domain.
Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions
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.
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary
Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners.
