Behavior Cloning in OpenAI using Case Based Reasoning

02/23/2020
by   Chad Peters, et al.
0

Learning from Observation (LfO), also known as Behavioral Cloning, is an approach for building software agents by recording the behavior of an expert (human or artificial) and using the recorded data to generate the required behavior. jLOAF is a platform that uses Case-Based Reasoning to achieve LfO. In this paper we interface jLOAF with the popular OpenAI Gym environment. Our experimental results show how our approach can be used to provide a baseline for comparison in this domain, as well as identify the strengths and weaknesses when dealing with environmental complexity.

READ FULL TEXT
research
05/13/2022

Modeling Human Behavior Part I – Learning and Belief Approaches

There is a clear desire to model and comprehend human behavior. Trends i...
research
10/07/2014

Ontology-based Representation and Reasoning on Process Models: A Logic Programming Approach

We propose a framework grounded in Logic Programming for representing an...
research
09/03/2021

Verification and Optimization of Cyber-Physical Systems: Preprint for FedCSIS

Optimizing CPS behavior in terms of energy consumption can have a signif...
research
07/29/2021

OpenSync: An opensource platform for synchronizing multiple measures in neuroscience experiments

Background: The human mind is multimodal. Yet most behavioral studies re...
research
02/18/2019

Using Machine Learning to Guide Cognitive Modeling: A Case Study in Moral Reasoning

Large-scale behavioral datasets enable researchers to use complex machin...
research
05/17/2022

A Multi-level Methodology for Behavioral Comparison of Software-Intensive Systems

Software-intensive systems constantly evolve. To prevent software change...
research
07/07/2022

Can Language Models perform Abductive Commonsense Reasoning?

Abductive Reasoning is a task of inferring the most plausible hypothesis...

Please sign up or login with your details

Forgot password? Click here to reset