Papers › A disembodied developmental robotic agent called Samu Bátfai

A disembodied developmental robotic agent called Samu Bátfai

9 Nov 2015arXiv:1511.02889archive 2025-07-28

Norbert Bátfai

The agent program, called Samu, is an experiment to build a disembodied DevRob (Developmental Robotics) chatter bot that can talk in a natural language like humans do. One of the main design feature is that Samu can be interacted with using only a character terminal. This is important not only for practical aspects of Turing test or Loebner prize, but also for the study of basic principles of Developmental Robotics. Our purpose is to create a rapid prototype of Q-learning with neural network approximators for Samu. We sketch out the early stages of the development process of this prototype, where Samu's task is to predict the next sentence of tales or conversations. The basic objective of this paper is to reach the same results using reinforcement learning with general function approximators that can be achieved by using the classical Q lookup table on small input samples. The paper is closed by an experiment that shows a significant improvement in Samu's learning when using LZW tree to narrow the number of possible Q-actions.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

15 repositories listed; official and paper-mentioned ones first.

nbatfai/amminadab officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/hezron officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/isaac officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/jacob officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/judah officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/perez officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/ram officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/samu officialmentioned in papermentioned on GitHubSyntology: not harvested report
nbatfai/Robopsychology mentioned on GitHubSyntology: not harvested report
nbatfai/SamuBrain mentioned on GitHubSyntology: not harvested report
nbatfai/SamuCTuring mentioned on GitHubSyntology: not harvested report
nbatfai/SamuKnows mentioned on GitHubSyntology: not harvested report
nbatfai/SamuLife mentioned on GitHubSyntology: not harvested report
nbatfai/SamuTuring mentioned on GitHubSyntology: not harvested report
nbatfai/nahshon mentioned on GitHubSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Q-LearningReinforcement LearningSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections