Search Results for author:
Found 19 papers, 5 papers with code
A Generalized Natural Actor-Critic Algorithm
In this paper, we describe a generalized Natural Gradient (gNG) by linearly interpolating the two FIMs and propose an efficient implementation for the gNG learning based on a theory of the estimating function, generalized Natural Actor-Critic (gNAC).
Multiple co-clustering based on nonparametric mixture models with heterogeneous marginal distributions
We propose a novel method for multiple clustering that assumes a co-clustering structure (partitions in both rows and columns of the data matrix) in each view.
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU).
Online Meta-learning by Parallel Algorithm Competition
In the OMPAC method, several instances of a reinforcement learning algorithm are run in parallel with small differences in the initial values of the meta-parameters.
Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming
Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks.
Unbounded Output Networks for Classification
In this study, by adopting features of the EE-RBM approach to feed-forward neural networks, we propose the UnBounded output network (UBnet) which is characterized by three features: (1) unbounded output units; (2) the target value of correct classification is set to a value much greater than one; and (3) the models are trained by a modified mean-squared error objective.
Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networks
Furthermore, we show that the self-developed compositionality of the network enhances faster re-learning when adapting to a new task that is a re-composition of previously learned sub-goals, than when starting from scratch.
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization.
Model-based Reinforcement Learning
reinforcement-learning
+1
Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning
We provide detailed theoretical analysis of the new algorithm that shows its efficiency and noise-tolerance inherited from Retrace and advantage learning.
MarmoNet: a pipeline for automated projection mapping of the common marmoset brain from whole-brain serial two-photon tomography
Understanding the connectivity in the brain is an important prerequisite for understanding how the brain processes information.
Variational Recurrent Models for Solving Partially Observable Control Tasks
In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve the task, and how to improve the policy.
Forward and inverse reinforcement learning sharing network weights and hyperparameters
A forward RL step minimizes the reverse KL estimated by the inverse RL step.
A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots
This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model(PGM)-based cognitive system to develop a cognitive system for developmental robots by integrating PGMs.
Canonical Cortical Circuits and the Duality of Bayesian Inference and Optimal Control
Here we consider the hypothesis that the sensory and motor cortical circuits implement the dual computations for Bayesian inference and optimal control, or perceptual and value-based decision making, respectively.
Goal-Directed Planning by Reinforcement Learning and Active Inference
Habitual behavior, which is obtained from the prior distribution of ${z}$, is acquired by reinforcement learning.
Variational oracle guiding for reinforcement learning
How to make intelligent decisions is a central problem in machine learning and cognitive science.
Tabular Data Imputation: Choose KNN over Deep Learning
As databases are ubiquitous nowadays, missing values constitute a pervasive problem for data analysis.
Habits and goals in synergy: a variational Bayesian framework for behavior
The habitual behavior is generated by using prior distribution of intention, which is goal-less; and the goal-directed behavior is generated by the posterior distribution of intention, which is conditioned on the goal.
Numerical Data Imputation for Multimodal Data Sets: A Probabilistic Nearest-Neighbor Kernel Density Approach
We compare our method with previous data imputation methods using artificial and real-world data with different data missing scenarios and various data missing rates, and show that our method can cope with complex original data structure, yields lower data imputation errors, and provides probabilistic estimates with higher likelihood than current methods.
