Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps
This addresses the challenge of building more human-like learning systems for robotics or AI, though it is incremental in combining existing unsupervised techniques.
The paper tackles the problem of enabling agents to learn intuitive physics and perform one-shot imitation through unsupervised exploration, using self-organizing maps and causal models. The result is demonstrated in the cartpole environment, where the agent flexibly solves related tasks after exploration.
Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration, and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future, and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.