Recent posts

Review 5

1 minute read

Making RL Tractable by Learning More Informative Reward Functions: Example-Based Control, Meta-Learning, and Normalized Maximum Likelihood.

Not Even Wrong

less than 1 minute read

Wow, I just found out what it means to be “Not even wrong”. The phase, coined by Wolfgang Pauli has just given me a huge slice of humble pie. Basically not e...