Oct 14 2010
Leave a comment
By Ari Weinstein Bandits, Continuous action spaces, Continuous state spaces, Sample Based Planning

BoB/HOLOP running in Swimmer domain


Pretty large MDP – it has 2 action dimensions and 9 state dimensions.

I’m using the parallelized version, running 500 trajectories of planning per step.  More information up later.

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s

%d bloggers like this: