Welcome to my field notes!
Field notes are notes I leave myself as I go through my day to day work. The hope is that other people will also find these notes useful. Note that these notes are unfiltered and unverified.
Reinforcement Learning in Julia
Reinforcement Learning has always interested me because I work in very data-sparse domains, and I view reinforcement learning as a way to overcome those data limitations at times.
ReinforcementLearning.jl
- There are tons of predefined experiments defined using the E string macro
- Components of each model
- Stop Condition: Used to determine when to stop an experiment such as
StopAfterSteporStopAfterEpisode - Hook: two-way callbacks format. There are some such as
TotalRewardPerEpisodeorStepsPerEpisodeto then be able to log metrics or do other things. - Environment: dictates things that the agent interacts with.
- Stop Condition: Used to determine when to stop an experiment such as
- There’s a whole new book
ReinforcementLearningAnIntroduction.jlthat has some Pluto notebooks to play with