Marek Rosa - dev blog: 02/01/2017

Monday, February 27, 2017

A blogpost about how the General AI Challenge is different from other AI challenges - by José Hernández-Orallo

The following is a blogpost published by José Hernández-Orallo, Professor at Technical University of Valencia and member of the General AI Challenge scientific advisory board.

I find Jose's article very interesting, especially how he summarizes our approach in reaching general artificial intelligence and how well he describes the benefits of gradual learning.

Below is only a brief preview. If you want to read more, please follow this link.

Preview:

When I was aware that the General AI Challenge was using CommAI-env for their warm-up round I was ecstatic. Participants could focus on RL agents without the complexities of vision and navigation. Of course, vision and navigation are very important for AI applications, but they create many extra complications if we want to understand (and evaluate) gradual learning. For instance, two equal tasks for which the texture of the walls changes can be seen as requiring higher transfer effort than two slightly different tasks with the same texture. In other words, this would be extra confounding factors that would make the analysis of task transfer and task dependencies much harder. It is then a wise choice to exclude this from the warm-up round. There will be occasions during other rounds of the challenge for including vision, navigation and other sorts of complex embodiment. Starting with a minimal interface to evaluate whether the agents are able to learn incrementally is not only a challenging but an important open problem for general AI.

Also, the warm-up round has modified CommAI-env in such a way that bits are packed into 8-bit (1 byte) characters. This makes the definition of tasks more intuitive and makes the ASCII coding transparent to the agents. Basically, the set of actions and observations is extended to 256. But interestingly, the set of observations and actions is the same, which allows many possibilities that are unusual in reinforcement learning, where these subsets are different. For instance, an agent with primitives such as “copy input to output” and other sequence transformation operators can compose them in order to solve the task. Variables, and other kinds of abstractions, play a key role.

Continue reading here.

Thank you,

Marek Rosa
CEO and Founder of Keen Software House
CEO, CTO of GoodAI

For more news:
General AI Challenge: www.general-ai-challenge.org
AI Roadmap Institute: www.roadmapinstitute.org
GoodAI: www.goodai.com
Space Engineers: www.spaceengineersgame.com
Medieval Engineers: www.medievalengineers.com

Personal bio: Marek Rosa is the CEO and CTO of GoodAI, a general artificial intelligence R&D company, and the CEO and founder of Keen Software House, an independent game development studio best known for their best-seller Space Engineers (2mil+ copies sold). Both companies are based in Prague, Czech Republic. Marek has been interested in artificial intelligence since childhood. Marek started his career as a programmer but later transitioned to a leadership role. After the success of the Keen Software House titles, Marek was able to personally fund GoodAI, his new general AI research company building human-level artificial intelligence, with $10mil. GoodAI started in January 2014 and has grown to an international team of 20 researchers.

Thursday, February 23, 2017

My thoughts on building general AI in a guest post for Singularity Weblog

SUMMARY:

Working towards my goal to create general AI; it will be a tool that will leverage discovery in every domain
Using game development to bootstrap GoodAI
The General AI Challenge is a way to crowdsource and diversify our search for human-level AI

The following is a blogpost I published on the Singularity Weblog. Below is only a brief preview. If you want to read more, please follow this link: www.singularityweblog.com/general-ai-challenge

Preview:

"Since my childhood, I have been working towards my goal of building human-level AI.

But I had two main areas of interest – game programming and artificial intelligence.

I spent my days and nights developing various real-time algorithms for computer graphics, aiming for a career in game development..."

Continue reading here.

Wednesday, February 15, 2017

First round of General AI Challenge just launched: Gradual Learning – Learning like a Human

SUMMARY:

First 6-month warm-up round just launched
Focus on “gradual learning” – because it’s an architecture property that enables gradual accumulation of skills, making learning more efficient
$50k in prizes in this round; $5mil in total prizes over the multi-year General AI Challenge

Today, we at GoodAI have launched our first warm-up round of the General AI Challenge.

It’s one of many stepping stones on our mission to develop general artificial intelligence - as fast as possible - to help humanity and understand the universe.

This first round focuses on “gradual learning” – which is the ability to gradually accumulate skills and use existing skills to learn new skills more efficiently.

The reason why we started with “gradual learning” is that we have identified it as an architecture property that will enable the efficient inclusion of additional properties. In other words, if you use your existing knowledge to learn to solve new problems, you should be more efficient than if you always have to start with zero experience.

The gradual learning round is not concerned with how good an agent is at solving a particular task (e.g. highest score in a game). Gradual learning is about how efficient an agent is at learning to solve new and unseen task. Using less training data and fewer computational resources is among the criteria for better agents.

Gradual learning requires a combination of at least these abilities: compositional learning, meta-learning / learning to learn, continuous learning, life-long learning, learning without forgetting, transfer learning and more. More info about “gradual learning” and other required properties for general AI is available in our framework document.

How this round works:

Today, teams start developing their AI / AGI agents
They can develop, test and train their agents on training tasks provided by us
All these tasks were designed with “graduality” in mind – which means that each task builds on skills acquired in previous tasks; each new task reuses skills learned in previous tasks
After 6 months, teams will submit their pre-trained agents / models and code
We will start evaluating the agents on non-public evaluation tasks
We will test the agent’s ability to learn gradually and to not-forget skills
The environment that we use for this round is a version of CommAI-Env. It is based on byte inputs and outputs and has text-like properties.
The training tasks are based on the CommAI-mini set recently proposed by Baroni et al., 2017 (https://arxiv.org/abs/1701.08954).
It may look like the agent is learning to communicate with the environment, however, our ultimate goal is not to build agents for this kind of environment. We chose it now because this type of environment makes it easier and more intuitive for people to understand why one task builds on top of a previous task. If we chose more complex and noisy environments (e.g. computer games), you would have a much harder time identifying when agents build skills on top of previously acquired skills.
However, our plan with the General AI Challenge is to scale to this level of complexity sooner or later.
Another reason for this environment was that during our road-mapping process we had identified “learned communication” as one of the essential skills which can speed up the acquisition of more advanced skills, and therefore increase the efficiency of learning (but this is something for later stages anyway)

Where are we aiming for with the General AI Challenge? We have identified a set of open problems that we consider to be key milestones in achieving general AI. Our teams here at GoodAI are working hard on solving these milestones but we also think that “outsourcing” to the greater community of researchers, programmers, and hackers can both speed up this process and diversify the avenues of research. We are also hoping that we may find new talented colleagues within the participating teams.

What if no team passes the evaluation in 6 months? Well, we will probably restart this same round again, perhaps with modified definitions and rules, or maybe slightly different evaluation tasks. There’s also a hope that if the participants get another chance, they will build on top of experience they gained in the first attempt which would eventually lead to a solution for gradual learning. In principle, the teams would then be gradually learning how to gradually learn :-)

We have allocated $5mil in total prize money for this multi-year challenge. We plan to distribute this pool of money to the participants of various rounds throughout the following years. We hope that we get to general AI before the money runs out :-)

Thank you for reading!

Marek Rosa
CEO and Founder of Keen Software House
CEO, CTO of GoodAI

For more news:
General AI Challenge: www.general-ai-challenge.org
AI Roadmap Institute: www.roadmapinstitute.org
GoodAI: www.goodai.com
Space Engineers: www.spaceengineersgame.com
Medieval Engineers: www.medievalengineers.com

Personal bio: Marek Rosa is the CEO and CTO of GoodAI, a general artificial intelligence R&D company, and the CEO and founder of Keen Software House, an independent game development studio best known for their best-seller Space Engineers (2mil+ copies sold). Both companies are based in Prague, Czech Republic. Marek has been interested in artificial intelligence since childhood. Marek started his career as a programmer but later transitioned to a leadership role. After the success of the Keen Software House titles, Marek was able to personally fund GoodAI, his new general AI research company building human-level artificial intelligence, with $10mil. GoodAI started in January 2014 and has grown to an international team of 20 researchers.