Learning from (Almost) Nothing. Christopher Crick. Talk

1. Basic idea is that robots are becoming more common, generating large amounts of data
   1. But the data is often poor; cheap, restricted sensors
2. Argues that humans are good at making alot from a small amount of information (Hieder and Simmel)
3. Deals a bit with nonstationarity where intents of agents can change in the middle of some interaction (the rules of who avoids who, chases who, in tag, for example)
4. Experiments very similar to what was done in my cog sci paper
5. Defines nonstationarity as a rapid change in mathematics of the estimated policy when it is represented as a polynomial
6. Talks about finding the rules from tag, and catch, but didnt yet discuss how the inference is performed or what the hypothesis space was
7. Learns faster when the machine can interact with the environment by testing hypothesis (active learning)
8. Work on humans training robots when the humans perception system is limited to that of the robots
   1. This allows instruction to work much better than if the human has a richer set of data to work from
9. Integration of heterogeneous sensing data from multiple robots