Controlling a unicycle with Policy Gradients
- Given that passive dynamic walkers and unicycles are dynamically similar to inverse pendulums, investigations on unicycle dynamics naturally lead to experiments on bipedal dynamics.
- Due to favorable trade-offs of effectiveness and model complexity I decided to start modelling unicycle behaviour using Policy Gradient methods.
code: Controlling a unicycle with Vanilla Policy Gradients
blog post: Controlling a unicycle with Policy Gradients
Understanding the free energy principle
- The free energy principle is a theory developed by Karl Friston and others to explain how biological systems tend to avoid disorder by limiting themselves to a small number of favorable states.
- Until recently, the Free Energy Principle has been a constant source of mockery from neuroscientists who misunderstood it and so I hope that by growing a collection of free-energy motivated reinforcement learning examples on Github we may finally have a constructive discussion between scientists.
- Regarding mockery, there is even a satirical Karl Friston account on Twitter.
code: Free Energy Experiments
blog post: Understanding the free energy principle
Is Causal Path Entropy an E=mc^2 for intelligence?
- The Causal Entropic Force framework proposes that organisms make decisions which maximise their future optionality.
- Alex Wissner-Gross, the main author of this theory thinks that this
is the closest thing to an E=mc^2 for intelligence.
- This repository is designed to help deconstruct this claim by analysing simple problems which provide insight into the limitations of Causal Entropic Forces.
code: Is Causal Path Entropy an E=mc^2 for intelligence?
blog post: Approximating Causal Path Entropy in Euclidean spaces
Fractals with TensorFlow:
- Right now, this repository is partly used to explore the symmetries of Mandelbrot variants.
- In the near future, I’ll add a GPU optimised version for investigating quaternion fractals.
- I wrote an introductory blog post for this repository.
code: Fractals with TensorFlow
blog post: Fractals with TensorFlow
- A set of tools for analysing deep fully-connected recitifer networks i.e. networks with ReLU activation.
- Specific tools include methods for analysing optimisation, variable disentangling, variable size representation,
sparsity, and generalisation.
- The ultimate goal is to develop useful mathematical models for deep rectifier networks, a model for supervised
learning that is not yet well-understood.
blog post: deep rectifier networks: preliminary observations