lefnire / tforce_btc_trader

TensorForce Bitcoin Trading Bot
http://ocdevel.com/podcasts/machine-learning/26
GNU Affero General Public License v3.0
820 stars 235 forks source link

Try ray/RLlib #11

Open lefnire opened 6 years ago

lefnire commented 6 years ago

[Update 2018-07-27] Update: seems Coach has slowed down (w/o much community), and rllab has stopped. A more recently popular framework is rllib (one letter different than rllab).


I'd like to try replacing TensorForce with Coach and see if we get any better performance. Use the Clipped PPO for an apples-to-apples comparison; instructions on converting our btc_env.py here.

History: before landing on TensorForce I'd tried rll/rllab and openai/baselines. Baselines is backed by OpenAI, the company behind half these algorithms (they're behind PPO, the model we're using). But baselines isn't a plug-n-play framework intended for developer use; instead it's a dumping-ground for each paper's corresponding sample code. I couldn't get any of their stuff customized to our use-case; all runs resulted eventually in NaNs everywhere. Coach is new. No hunch as to whether it'll outperform, though it is backed by Intel which bodes well. I want to give it a whirl, but don't have time right now - so if anyone wants to take a stab at it, please indeed!

datctbk commented 6 years ago

hi Sir! can I help you that?

lefnire commented 6 years ago

Sorry late, I'm AFK from the project till July. Would be great if you could take a look! I've seen a lot of activity on both projects, just from Git commits, so I think it'd be good to have a comparison between the two.