Machine Learning Assets for Games and Scientific Computing
Making leading-edge algorithms available to the full range of software developers
In humans and many mammals, the decision making system that underpins our emotions takes the form of dopamine based model-free reinforcement learning (intuitive, unconscious decisions making). The Q-learning algorithm can approximate these strategic decisions and is used in the toolkit to generate behaviors that then drive the agent's emotional response. Download Now
Model Free Reinforcement Learning can be used to provide an AI or with intentional behavior including avoiding enemy players, collecting health points, and many of the strategies a human is capable of manifesting within a game environment. With our Neurostudio DQN Engine, instead of having to create complex hand-crafted behavior trees, simply reward the actions you want the agent to take and watch as it learns strategies on its own to recieve these rewards.Download Now
Causal inference remains one of the hard nuts to crack in Artificial Intelligence. Bringing Reinforcement Learning methods to bear on the topic is unlocking new frontiers in casual inference and is an area of ongoing research for us.