The Cross Entropy Method (CEM) is a generic optimization technique. It is a zero-th order method, i.e. you don’t gradients.1 So, for instance, it works well on combinatorial optimization problems, as well as reinforcement learning.Continue reading “Cross Entropy Method”
The exponential family of distributions are a particularly tractable, yet broad, class of probability distributions. They are tractable because of a particularly nice [Fenchel] duality relationship between natural parameters and moment parameters. Moment parameters can be estimated by taking the empirical mean of sufficient statistics and the duality relationship can then recover an estimate of the distributions natural parameters.Continue reading “Exponential Families”
This is a quick note on policy gradients in bandit problems. There are a number of excellent papers coming out on the convergence of policy gradients [1 ,2, 3]. I wrote this sketch argument a few months ago. Lockdown and homeschooling started and I found I did not have time to pursue it. Then yesterday morning I came across the following paper Mei et al. , which uses a different Lyapunov argument to draw an essentially the same conclusion [first for bandits then for general RL]. Although most of the time I don’t talk about my own research on this blog, I wrote this short note here just in case this different Lyapunov argument is of interest.
Further, all these results on policy gradient are [thus far] for deterministic models. I wrote a short paper that deals with a stochastic regret bound for a policy gradient algorithm much closer to projected gradient descent, again in the bandit setting. I’ll summarize this, as it might be possible to use it to derive stochastic regret bounds for policy gradients more generally. At the end, I discuss some issues around getting some proofs to work in the stochastic case and emphasize the point that is a good choice of lyapunov function [where $latex $q^\star$ is the probability of not choosing the optimal action.]Continue reading “A Short Discussion on Policy Gradients in Bandits”
I’ve updated the stochastic control notes here:
These still remain a work in progress.
(Typos/errors/mishaps found are welcome)
A quick summary of what is new:
- I’ve updated a section on the ODE method for stochastic approximation.
- I’ve improved the discussion around Temporal Difference methods and included some proofs.
- I’ve added a proof of convergence for SARSA.
- I’ve added a section on Lyapunov functions in continuous time
- La Salle, exponential convergence, and online convex optimization…
- I’ve started a section on Policy Gradients but there is more recent proofs to include
- I’ve started a section on Deep Learning for RL.
We consider the Robbins-Monro update
and argue that this can be approximated by the o.d.e.: