An Open-World Simulated Environment for Developmental Robotics

07/18/2020
by   SM Mazharul Islam, et al.
0

As the current trend of artificial intelligence is shifting towards self-supervised learning, conventional norms such as highly curated domain-specific data, application-specific learning models, extrinsic reward based learning policies etc. might not provide with the suitable ground for such developments. In this paper, we introduce SEDRo, a Simulated Environment for Developmental Robotics which allows a learning agent to have similar experiences that a human infant goes through from the fetus stage up to 12 months. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model.

READ FULL TEXT
research
09/03/2020

SEDRo: A Simulated Environment for Developmental Robotics

Even with impressive advances in application-specific models, we still l...
research
12/29/2020

Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics

Task-specific AI agents are showing remarkable performance across differ...
research
08/09/2021

Toward Human-Level Artificial Intelligence

In this paper, we present our research on programming human-level artifi...
research
06/11/2019

Learning Powerful Policies by Using Consistent Dynamics Model

Model-based Reinforcement Learning approaches have the promise of being ...
research
01/05/2023

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

Developing agents that can execute multiple skills by learning from pre-...
research
11/18/2020

Language Acquisition Environment for Human-Level Artificial Intelligence

Despite recent advances in many application-specific domains, we do not ...
research
12/30/2022

An Entropy-Based Model for Hierarchical Learning

Machine learning is the dominant approach to artificial intelligence, th...

Please sign up or login with your details

Forgot password? Click here to reset