Learn More
This work presents a novel learning method in the context of embodied artificial intelligence and self-organization, which has as few assumptions and restrictions as possible about the world and the underlying model. The learning rule is derived from the principle of maximizing the predictive information in the sensorimotor loop. It is evaluated on robot(More)
Even if the character of robotics is primarily technological, it was always closely connected with biology right from the beginning. However, most of the time this was only a one-way relationship, for biological insights were often used as a pool of approved ideas and methods to find solutions for rudimentary problems in robotics (walking machines in(More)
SFI Working Papers contain accounts of scienti5ic work of the author(s) and do not necessarily represent the views of the Santa Fe Institute. We accept papers intended for publication in peer-­‐reviewed journals or proceedings volumes, but not papers that have already appeared in print. Except for papers by our external faculty, papers must be based on work(More)
It is claimed that synaptic plasticity of neural controllers for autonomous robots can enhance the behavioral properties of these systems. Based on homeostatic properties of so called self-regulating neu-rons, the presented mechanism will vary the synaptic strength during the robot interaction with the environment, due to driving sensor inputs and motor(More)
We consider the causal structure of the sensorimo-tor loop (SML) and represent the agent's policies in terms of conditional restricted Boltzmann machines (CRBMs). CRBMs can model non-trivial conditional distributions on high dimensional input-output spaces with relatively few parameters. In addition, their Glauber dynamics can be computed efficiently to(More)
One of the main challenges in the field of embodied artificial intelligence is the open-ended autonomous learning of complex behaviors. Our approach is to use task-independent, information-driven intrinsic motivation(s) to support task-dependent learning. The work presented here is a preliminary step in which we investigate the predictive information (the(More)