Search results for "Imitation Learning"

Imitation Learning and Anchoring through Conceptual Spaces

2007

In order to have a robotic system able to effectively learn by imitation and not merely reproduce the movements of a human teacher, the system should have the capability to deeply understand the perceived actions to be imitated. This paper deals with the development of a cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. The purpose of the following discussion is to show how the same conceptual representation can be used both in a bottom-up approach, in order to learn sequences of actions by imitation learning paradigm, and in a top-down approach, in order to anchor the symbolical representations to the perceptual act…

A Cognitive Framework for Imitation Learning

2006

Abstract In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the perceived actions to be imitated. This paper deals with the development of cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. The purpose of the following discussion is to show how this Conceptual Area can be employed to efficiently organize perceptual data, to learn movement primitives from human demonstration and to generate complex actions by combining and sequencing simpler ones. The proposed architecture ha…

Sing with the Telenoid

2012

We introduce a novel research proposal project aimed to build a robotic setup in which the Telenoid learns to improvise jazz singing in a duet with a human singer. In the proposed application, the Telenoid acts in teleoperated mode during the learning phase, while it becomes more and more autonomous during the working phase. A goal of the research is to investigate the essence of human communication which is based on gestures and prosody. We will employ an architecture for imitation learning that incrementally learns from demonstrations sequences of internal model activations, based on the idea of coupled forward- inverse internal models for representing musical phrases and the body sequenc…

Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples

2022

In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. We require that an offline expert assesses the value of a state in a coarse manner using three discrete values. An expert network is designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a…

An Architecture for Observational Learning

2014

In this thesis I present an architecture that learns new skills through observation and adapts to the environment through situated experience in the world. Such an architectural growth is bootstrapped from a minimal initial knowledge and the architecture itself is built around the biologically-inspired notion of internal models. The key idea, supported by findings in cognitive neuroscience, is that the same internal models used in overt goal-directed action execution can be covertly re-enacted in simulation to observe and understand the actions of others. The system applies these concepts to learning higher order cognitive functions like learning problem solving skills and social interactio…

A Cognitive Framework for Learning by Imitation

2005

Representation, Recognition and Generation of Actions in the Context of Imitation Learning

2006

The paper deals with the development of a cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. We adopt the paradigm of conceptual spaces, in which static and dynamic entities are employed to efficiently organize perceptual data, to recognize positional relations, to learn movements from human demonstration and to generate complex actions by combining and sequencing simpler ones. The aim is to have a robotic system able to effectively learn by imitation and which has the capabilities of deeply understanding the perceived actions to be imitated. Experimentation has been performed on a robotic system composed of a PUMA 20…

Learning high-level manipulative tasks through imitation

2006

This paper presents ConSCIS, Conceptual Space based Cognitive Imitation System, which tightly links low-level data processing with knowledge representation in the context of robot imitation. Our focus is on the program-level imitation: we are interested in the final effects of actions on objects, and not on the particular kinematic or dynamic properties of the motion. The same architecture is used both to analyze and represent the task to be imitated, and to perform the imitation by generalizing in novel and different circumstances. The implemented experimental scenario is a two dimensional world populated with various objects in which observation/imitation takes place. To validate our appr…

An architecture for observational learning and decision making based on internal models

2013

We present a cognitive architecture whose main constituents are allowed to grow through a situated experience in the world. Such an architectural growth is bootstrapped from a minimal initial knowledge and the architecture itself is built around the biologically-inspired notion of internal models. The key idea, supported by findings in cognitive neuroscience, is that the same internal models used in overt goal-directed action execution can be covertly re-enacted in simulation to provide a unifying explanation to a number of apparently unrelated individual and social phenomena, such as state estimation, action and intention understanding, imitation learning and mindreading. Thus, rather than…

Learning high-level tasks through imitation

2006

This paper presents the cognitive architecture Con-SCIS (Conceptual Space based Cognitive Imitation System), which tightly links low-level data processing with knowledge representation in the context of imitation learning. We use the word imitate to refer to the paradigm of program-level imitation: we are interested in the final effects of actions on objects, and not on the particular kinematic or dynamic properties of the motion. The same architecture is used both to analyze and represent the task to be imitated, and to perform the imitation by generalizing in novel and different circumstances. The implemented experimental scenario is a simplified two-dimensional world populated with vario…