Neoteric Dinner Party

chevron-icon
RFP Proposals
Top
chevron-icon
project-presentation-img
Expert Rating 4.0
Soumil Rathi
Project Owner

Neoteric Dinner Party

Expert Rating

4.0

Overview

MeTTa was designed as a language for AGI, yet there is a noticeable lack of agent-based demos showcasing its full potential. This proposal seeks to address that gap through an innovative project that highlights MeTTa’s unique capabilities. This project proposes a MeTTa-based simulation of a virtual dinner party involving neoteric agents with dynamic goal-setting, procedural learning, and introspective reasoning. Each agent will have their own goals to hit during the dinner party. With their goals and knowledge stored in their Atomspace, each agent will be able to recursively subdivide their current goal, thus taking the best action at the moment to eventually reach their goal.

RFP Guidelines

Develop interesting demos in MeTTa

Complete & Awarded
  • Type SingularityNET RFP
  • Total RFP Funding $100,000 USD
  • Proposals 21
  • Awarded Projects 4
author-img
SingularityNET
Aug. 12, 2024

Create educational and/or useful demos using SingularityNET's own MeTTa programming language. This RFP aims at bringing more community adoption of MeTTa and engagement within our ecosystem, and to demonstrate and expand the utility of MeTTa. Researchers must maintain demos for a minimum of one year.

Proposal Description

Project details

The project aims to showcase the capabilities of the MeTTa programming language by creating a dynamic simulation of a dinner party attended by virtual agents, or "neoterics." Each agent will be assigned a primary goal for the party, such as forming connections, maximizing personal enjoyment, or ensuring harmony at the table. These agents will autonomously recursively break their current goal into subgoals, plan their actions, and interact with each other to achieve their objectives.

Key features include:

  • Goal-Driven Behavior: Agents will use MeTTa's multiparadigm programming features to derive actionable sub-goals and plan sequences based on their main objectives.

  • Procedural Learning: Agents will modify their internal rules and behavior patterns through interactions, allowing them to adapt and improve over time. This learning will be represented in their Atomspace, enabling persistent updates to their knowledge and logic.

  • Action Justification: When agents perform an action, they will provide an insight into their current knowledge, goals, and reasoning process. This feature leverages MeTTa’s rule-matching and reasoning capabilities, making the decision-making process transparent to users.

  • Interactive Demo: Users will be able to change the initial goals and preferences for each agent, enabling them to steer the simulation’s dynamics. This allows the audience to see how different initial setups affect agent interactions and outcomes.

  • Autonomous Control: This demo will directly connect MeTTa with neoterics in the SophiaVerse, allowing the program to control these agents interactively in real-time.

The demonstration will emphasize MeTTa's key strengths:

  • Self Modifying: Agents will alter their internal rules as they learn, showcasing MeTTa’s ability to handle procedural learning.

  • Probabilistic Logic: Agents will use probabilistic logic to create subgoals and decide actions, to account for incomplete and uncertain information.

  • Knowledge Representation: Agents’ goals, plans, and learned knowledge will be stored in Atomspace and queried dynamically during the simulation.

  • Recursive Expressions: The simulation will require all neoterics to recursively divide their current goals into smaller and easier sub-goals to execute, showing off the ability of MeTTa to handle recursive computations effectively.

  • Grounding: The demo will show the ability of MeTTa to ground with external actions and abilities to effectively create a hybrid neuro-symbolic system for each agent.

This simulation will serve as an engaging and practical illustration of MeTTa's potential to model and execute complex, adaptive systems, positioning it as a powerful tool for AGI-related research and applications.

Open Source Licensing

Apache License

Proposal Video

Not Avaliable Yet

Check back later during the Feedback & Selection period for the RFP that is proposal is applied to.

  • Total Milestones

    5

  • Total Budget

    $25,000 USD

  • Last Updated

    4 Dec 2024

Milestone 1 - Setup

Description

This milestone will handle the setup for the environment and all of its agents. This includes the larger environment with the dinner party environment and each of the different agents within SophiaVerse. Moreover the milestone also includes the structure setup for an agent as MeTTa programs. Finally, it also includes setting up the agents - the states, goals, memory and actions that any agent can take.

Deliverables

The overall deliverable for this milestone is a setup for the multi-agent environment. For each agent, the states, actions, goals will be defined within MeTTa, and the memory component will be initialized. The format of the deliverable will be the codebase.

Budget

$3,000 USD

Success Criterion

A successful implementation would allow an agent to be setup within the dinner party environment within SophiaVerse. This agent would be able to have its goals and potential actions setup.

Milestone 2 - Action Execution

Description

This milestone refers to the integration of the MeTTa program with the SophiaVerse environment. As a part of this milestone the agent will be able to execute any selected actions which will run within the SophiaVerse environment as well.

Deliverables

The deliverable for this milestone would be the codebase for the demo with the integration within MeTTa to execute actions in the SophiaVerse. This effectively means that actions will be mapped from Atomspace states to grounded functions.

Budget

$2,000 USD

Success Criterion

A successful implementation of this milestone will have an agent setup within MeTTa that can take actions within SophiaVerse when explicitly programmed. For example, the agent could be told to walk forward, speak, pick up things, eat, and would be able to execute such actions within the multi agent environment.

Milestone 3 - Rule Creation

Description

The most important thing for an agent is to create sub-goals and use the state information to map to the best action at the time. This milestone will address that creating rules for each of those mappings such that the agent can autonomously run. The matching would be based on probabilistic logic with MeTTa’s pattern-matching.

Deliverables

Once again, the primary deliverable will be the codebase. Within this codebase, all MeTTa rules for subgoal creation and action mapping will have been created and implemented. Thus, within this codebase, agents would be able to operate autonomously within the constraints of its defined goals.

Budget

$10,000 USD

Success Criterion

A successful implementation of this milestone would have an agent able to decide which action to take based on its goals. This agent, when given a goal (eg. pick up a particular) object, would be able to break down the goal into subgoals continuously (eg. face object, reach object, pick up object).

Milestone 4 - Learning

Description

This milestone refers to each agent being able to learn and update from its experiences in the environment. This includes gaining knowledge from the environment as it runs such as information about other agents and the environment. It also includes getting better at certain actions and goals by updating internal probabilities of success for undertaken actions.

Deliverables

Once again, the deliverable for this milestone will be the codebase at the current stage. At this level, the MeTTa rules and functions for identifying / gaining information from the environment will have been setup. This includes having functions to update probabilities of certain actions and goals based on learned experience.

Budget

$9,000 USD

Success Criterion

A successful implementation of this milestone will see the agent learning from any mistakes it makes, or any actions that don't work in the environment (limited by the defined rules). As an example, if other agents are unfriendly to it, it would be able to perceive this and use that information to update it's internal goals and actions, such as removing a goal to become their field.

Milestone 5 - Documentation + Deployment

Description

This milestone covers the final work for the proposal - writing all required documentation and deploying the project. The documentation includes the full structure and functionality of the environment as well as each individual reason. It also includes a technical report about the demo. Experiments will be conducted with the interactive demo with different starting goals and will be included in the technical report. Finally I will create a video explaining the demo structure and functionality to make it easy to follow. The code will be deployed in a Hyperon instance hosted by SingularityNET.

Deliverables

This milestone includes the final deliverables for the proposal. It will contain the full codebase under an appropriate open source license. This codebase will be deployed on a public Hyperon instance. Finally, all relevant documentation will be written and provided, including video and technical report

Budget

$1,000 USD

Success Criterion

A successful implementation of this milestone will mean that the Hyperon instance running the codebase is running without any errors, the codebase itself is documented and maintained, and that the documentation is extensive and well-written enough to be understood by other developers, and that the code is extensible in the future.

Join the Discussion (0)

Expert Ratings

Reviews & Ratings

Group Expert Rating (Final)

Overall

4.0

  • Feasibility 4.0
  • Desirabilty 4.0
  • Usefulness 2.7

While reviewers rated this submission highly, ultimately the panel of experts selected another proposal for strategic reasons.

  • Expert Review 1

    Overall

    4.0

    • Compliance with RFP requirements 4.0
    • Solution details and team expertise 4.0
    • Value for money 2.0
    Unclear about team capabilities

    Strong alignment with RFP goals. Technically ambitious demo showcasing MeTTa’s capabilities in multi-agent goal-setting, procedural learning, and introspection. Highlights MeTTa’s potential for recursive reasoning and neuro-symbolic integration in Sophiaverse. Deliverables are well-defined, but team credibility and prior experience in MeTTa or multi-agent systems are not detailed.

  • Expert Review 2

    Overall

    3.0

    • Compliance with RFP requirements 3.0
    • Solution details and team expertise 3.0
    • Value for money 2.0

  • Expert Review 3

    Overall

    5.0

    • Compliance with RFP requirements 5.0
    • Solution details and team expertise 5.0
    • Value for money 4.0
    This would be a nice demo and fits in with our goals for the Neoterics proto-AGI playground

    Conceptually this is straightforward and makes a lot of sense, so the focus would be on getting the various implementation details ironed out. Then the actual proto-AGI experimentation would probably run beyond the scope of this grant but could be pursued afterwards with additional grants or otherwise, potentially...

feedback_icon