Badger architecture is the unifying framework for our research defined by its key principle modular life-long learning.
The modular aspect is expressed in the architecture through a network of identical agents. The life-long learning means that the network will be capable of adapting to a growing (open-ended) range of new and unseen tasks while being able to reuse knowledge acquired in previous tasks. The algorithm that is run by individual Badger modules (a.k.a. experts) will be discovered through meta-learning.
We expect the design principles of Badger architecture to be its key advantages. The modular approach should enable scaling beyond what is possible for a monolithic system and the focus on life-long learning will allow for incremental, piece-wise learning, driving down the demand for training data.
State of Badger
Below you can find a taster of some of our latest work.
Most modern AI scales with the availability of data – to improve its performance or behavior requires more and more data taken from the world. The promise of Badger is to give scalable computational resources, as increasing numbers of experts could be added at runtime. So how do we turn that into an advantage, if data is the limit? One kind of method that does scale with compute is AI that integrates some sort of search component over a model of the world – for example, the successes of Monte-Carlo Tree Search and AlphaGo. However, in those games, a perfect model of the world can be provided. For AI that will generalize and scale to real-world, formerly unseen problems, we need to become good at learning such models.
The above videos are examples from a model learned from videos of a particle simulation. In particular, this is a model that can generate not just one future but an entire distribution of possible futures – a distribution that could be searched in parallel by multiple nodes, with their discoveries then networked together via communication in order to formulate a decision.
Principles of Badger
Badger is an architecture and a learning procedure where:
- An agent is made up of many experts
- All experts share the same communication policy (expert policy), but have different internal memory states
- There are two levels of learning, an inner loop (with a communication stage) and an outer loop
- Inner loop – Agent’s behavior and adaptation emerges as a result of experts communicating between each other. Experts send messages (of any complexity) to each other and update their internal memories/states based on observations/messages and their internal state from the previous time-step. Expert policy is fixed and does not change during the inner loop.
- Inner loop loss need not even be a proper loss function. It can be any kind of structured feedback so long as it eventually relates to the outer loop performance.
- Outer loop – An expert policy is discovered over generations of agents, ensuring that strategies that find solutions to problems in diverse environments can quickly emerge in the inner loop.
- Agent’s objective is to adapt fast to novel tasks
- Open-ended inner loop learning needs to be enabled by a suitable design of the outer loop, for instance through the support of agent self-reference and by using curiosity as an implicit agent goal creation mechanism. An open-ended agent should be able to come up with novel and creative solutions to problems it faces. The environment it operates in needs to be open-ended too – it must enable creation of novel and unforeseen tasks that match the current skill level of the agent, to support its further improvement.
Exhibiting the following novel properties:
- Roles of experts and connectivity among them assigned dynamically at inference time
- Learned communication protocol with context-dependent messages of varied complexity
- Generalizes to different numbers and types of inputs/outputs
- Can be trained to handle variations in architecture during both training and testing
The animation above shows 10 layers of a cellular automaton evolving over time. The task is to copy the pattern from the middle to one of the dots – not both. Thus, the distributed agent has to learn a coordination strategy to determine which dot will be active. The second animation demonstrates a “transform” task, where the pattern has to be modified during the copying process. Additionally, regularization in the form of cell activation zeroing is present. The policies unfolding above have been found by SGD.
The aim of this project is to develop a new game - code name AI Game - where freeform dialogs between player and game characters take a major role.
In the game, players interact with game characters controlled by large-language models, where the language models simulate the behavior of people in both responses and actions, displaying complex personalities with goals, emotions, and memories.
Large language models are neural networks trained on internet-scale text corpora with one objective: to predict the next word. During gameplay, the game feeds the game character’s personality (described by designers in plain text), observations, recent events, and dialogues to a large language model, which then predicts what this person in this situation would do, think, and say (emulating their personality). This output is then translated to game actions. The current system is hybrid, relying on large language models, but also on traditional planner technology. In the future, we expect that the large language models will do planning too. This new approach to AI-driven characters leads to **non-scripted behavior, complex and richer personalities, and more emergent gameplay.
GoodAI started as a research and development initiative inside Keen Software House in January 2014, when CEO Marek Rosa invested $10M USD into the project.
At Good AI we are focused on 3 areas
- Research of AGI
- Applied AI & Robotics
- AI Game development
Our long-term goal is to build general artificial intelligence that will automate cognitive processes in science, technology, business, and other fields. We conduct our own research, advocate fundamental AI research at the EU governmental level, and forge a community of like-minded groups through the GoodAI Grants program.
GoodAI is a company with around 30 talented people working all across the world.
GoodAI stands apart from other AI companies because of our roadmap, framework, and big-picture view. We pursue general AI with a long-term, 10+ year vision, and remain dedicated to this goal. We will not be distracted by narrow AI approaches or short-term commercialization, though we are certain to find useful applications for our general AI technology along the way.
Our roadmap, framework, and experimental implementations are at a very early stage and should be taken as works in progress. We are focused on the gradual accumulation of skills and recursive self-improvement. We do research in growing network topologies and modular networks and train and teach our AI in our School for AI.
At GoodAI, we want to create a positive future for everyone. Developing general AI will be the most helpful thing in human history, and we want to help make this dream come true.
We’re looking for people with experience from the research companies focused on 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐢𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞 but also 𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 or 𝐑𝐨𝐛𝐨𝐭𝐢𝐜𝐬.
Our company culture is defined by goals, rather than standards. We believe that there is always room for improvement and innovation. Adapting our goals and striving for improvement, rather than complacency and merely meeting some standard is at the core of our values.
Strive to establish a positive company culture and ensure our teams understand why our company culture plays a huge role in our success. Every team member can take action to strengthen us, as a company, and ensure we deliver only our best.
𝐏𝐫𝐨𝐯𝐢𝐝𝐞 𝐩𝐞𝐨𝐩𝐥𝐞 𝐰𝐢𝐭𝐡 𝐠𝐨𝐨𝐝 𝐰𝐨𝐫𝐤𝐢𝐧𝐠 𝐜𝐨𝐧𝐝𝐢𝐭𝐢𝐨𝐧𝐬. This includes our intern policy, equal opportunity, advanced education and personal development, flexibility, participation in external activities, and more.
We are a group of very curious people who share hobbies and interests, not just in the area of AI, science, and video games, but in a broad range of pursuits like mountain climbing, drones, or Roman architecture.
𝐎𝐭𝐡𝐞𝐫 𝐭𝐡𝐢𝐧𝐠𝐬 𝐭𝐡𝐚𝐭 𝐦𝐢𝐠𝐡𝐭 𝐢𝐧𝐭𝐞𝐫𝐞𝐬𝐭𝐬 𝐲𝐨𝐮:
- Company breakfasts and snacks.
- On-site gym and private garden.
- Office which looks like home.
- Team-buildings and parties.
- Private Chef Ceejay making us delicious lunch everyday.
- Private Psychologist and life coach Misa, ready to help you handle any challenges you may have.
- 𝐑𝐞𝐬𝐮𝐥𝐭𝐬-𝐨𝐫𝐢𝐞𝐧𝐭𝐞𝐝: we measure ourselves only by our results.
- 𝐍𝐨 𝐥𝐢𝐦𝐢𝐭𝐬: we can achieve anything; we are pushing our limits in technology and art.
- 𝐈𝐧𝐭𝐞𝐠𝐫𝐢𝐭𝐲: we have the courage to do the right thing, regardless of the consequences and the inconvenience.
- 𝐄𝐱𝐭𝐫𝐞𝐦𝐞 𝐨𝐰𝐧𝐞𝐫𝐬𝐡𝐢𝐩: It does not matter if you are a leader or an individual contributor. Every team member accepts accountability and equal responsibility for our collaborative effort.
- 𝐄𝐱𝐜𝐞𝐥𝐥𝐞𝐧𝐜𝐞 𝐢𝐧 𝐞𝐱𝐞𝐜𝐮𝐭𝐢𝐨𝐧: Our teams aim for excellence in everything we do – What you tolerate is what you will end up with.
- 𝐒𝐢𝐦𝐩𝐥𝐢𝐜𝐢𝐭𝐲 𝐢𝐧 𝐝𝐞𝐬𝐢𝐠𝐧: less is better; avoid feature creep; simplicity is the ultimate sophistication.
- 𝐓𝐞𝐚𝐦𝐰𝐨𝐫𝐤: we treat our colleagues with respect, supporting each other throughout to ensure we maximize the value for everyone while creating an atmosphere of trust.