Richard Jozsa
5980431b91
Merge branch 'freqtrade:feat/freqai-rl-dev' into feat/freqai-rl-dev
2022-08-29 16:44:09 +02:00
Richard Jozsa
1a8e1362a1
There was an error in the docs around continual learning and thread count ( #7314 )
...
* Error in the docs
2022-08-29 11:15:06 +02:00
richardjozsa
8c497c4abf
Error in the docs
2022-08-29 10:04:39 +02:00
richardjozsa
5709a0d2ff
Merge branch 'feat/freqai-rl-dev' of https://github.com/richardjozsa/freqtrade into feat/freqai-rl-dev
2022-08-28 23:27:33 +02:00
robcaulk
67cddae756
fix tensorboard image
2022-08-28 21:00:26 +02:00
robcaulk
af8f308584
start the reinforcement learning doc
2022-08-28 20:52:03 +02:00
robcaulk
7766350c15
refactor environment inheritence tree to accommodate flexible action types/counts. fix bug in train profit handling
2022-08-28 19:21:57 +02:00
richardjozsa
5ccd80eda6
Conception problem with the unrealized profit
...
I think here is a conception problem with the total profit, if we *= it with the last PnL it means we assume that the last profit effects on this one. In real life it depends on the user eg stake amount can be unlimited.
However the agent will learn better and more if we just add it with +=.
2022-08-27 00:49:48 +02:00
robcaulk
8c313b431d
remove whitespace from Dockerfile
2022-08-26 11:14:01 +02:00
robcaulk
baa4f8e3d0
remove Base3ActionEnv in favor of Base4Action
2022-08-26 11:04:25 +02:00
richardjozsa
cdc550da9a
Revert the docker changes to be inline with the original freqtrade image
...
Reverted the changes, and added a new way of doing, Dockerfile.freqai with that file the users can make their own dockerimage.
2022-08-26 11:04:25 +02:00
richardjozsa
d31926efdf
Added Base4Action
2022-08-26 11:04:25 +02:00
robcaulk
3199eb453b
reduce code for base use-case, ensure multiproc inherits custom env, add ability to limit ram use.
2022-08-25 19:05:51 +02:00
robcaulk
05ccebf9a1
automate eval freq in multiproc
2022-08-25 12:29:48 +02:00
robcaulk
94cfc8e63f
fix multiproc callback, add continual learning to multiproc, fix totalprofit bug in env, set eval_freq automatically, improve default reward
2022-08-25 11:46:18 +02:00
robcaulk
d1bee29b1e
improve default reward, fix bugs in environment
2022-08-24 18:32:40 +02:00
robcaulk
a61821e1c6
remove monitor log
2022-08-24 16:33:13 +02:00
robcaulk
bd870e2331
fix monitor bug, set default values in case user doesnt set params
2022-08-24 16:32:14 +02:00
robcaulk
c0cee5df07
add continual retraining feature, handly mypy typing reqs, improve docstrings
2022-08-24 13:00:55 +02:00
robcaulk
b708134c1a
switch multiproc thread count to rl_config definition
2022-08-24 13:00:55 +02:00
robcaulk
b26ed7dea4
fix generic reward, add time duration to reward
2022-08-24 13:00:55 +02:00
robcaulk
280a1dc3f8
add live rate, add trade duration
2022-08-24 13:00:55 +02:00
robcaulk
f9a49744e6
add strategy to the freqai object
2022-08-24 13:00:55 +02:00
richardjozsa
a2a4bc05db
Fix the state profit calculation logic
2022-08-24 13:00:55 +02:00
robcaulk
29f0e01c4a
expose environment reward parameters to the user config
2022-08-24 13:00:55 +02:00
robcaulk
d88a0dbf82
add sb3_contrib models to the available agents. include sb3_contrib in requirements.
2022-08-24 13:00:55 +02:00
robcaulk
8b3a8234ac
fix env bug, allow example strat to short
2022-08-24 13:00:55 +02:00
mrzdev
8cd4daad0a
Feat/freqai rl dev ( #7 )
...
* access trades through get_trades_proxy method to allow backtesting
2022-08-24 13:00:55 +02:00
robcaulk
3eb897c2f8
reuse callback, allow user to acces all stable_baselines3 agents via config
2022-08-24 13:00:55 +02:00
robcaulk
4b9499e321
improve nomenclature and fix short exit bug
2022-08-24 13:00:55 +02:00
sonnhfit
4baa36bdcf
fix persist a single training environment for PPO
2022-08-24 13:00:55 +02:00
robcaulk
f95602f6bd
persist a single training environment.
2022-08-24 13:00:55 +02:00
robcaulk
5d4e5e69fe
reinforce training with state info, reinforce prediction with state info, restructure config to accommodate all parameters from any user imported model type. Set 5Act to default env on TDQN. Clean example config.
2022-08-24 13:00:55 +02:00
sonnhfit
7962a1439b
remove keep low profit
2022-08-24 13:00:55 +02:00
sonnhfit
81b5aa66e8
make env keep current position when low profit
2022-08-24 13:00:55 +02:00
sonnhfit
45218faeb0
fix coding convention
2022-08-24 13:00:55 +02:00
richardjozsa
d55092ff17
Docker building update, and TDQN repair with the newer release of SB+
2022-08-24 13:00:55 +02:00
robcaulk
74e4fd0633
ensure config example can work with backtesting RL
2022-08-24 13:00:55 +02:00
robcaulk
b90da46b1b
improve price df handling to enable backtesting
2022-08-24 13:00:55 +02:00
MukavaValkku
2080ff86ed
5ac base fixes in logic
2022-08-24 13:00:55 +02:00
robcaulk
16cec7dfbd
fix save/reload functionality for stablebaselines
2022-08-24 13:00:55 +02:00
sonnhfit
0475b7cb18
remove unuse code and fix coding conventions
2022-08-24 13:00:55 +02:00
MukavaValkku
d60a166fbf
multiproc TDQN with xtra callbacks
2022-08-24 13:00:55 +02:00
robcaulk
dd382dd370
add monitor to eval env so that multiproc can save best_model
2022-08-24 13:00:55 +02:00
robcaulk
69d542d3e2
match config and strats to upstream freqai
2022-08-24 13:00:55 +02:00
robcaulk
e5df39e891
ensuring best_model is placed in ram and saved to disk and loaded from disk
2022-08-24 13:00:55 +02:00
robcaulk
bf7ceba958
set cpu threads in config
2022-08-24 13:00:55 +02:00
MukavaValkku
57c488a6f1
learning_rate + multicpu changes
2022-08-24 13:00:55 +02:00
MukavaValkku
48bb51b458
example config added
2022-08-24 13:00:55 +02:00
MukavaValkku
b1fc5a06ca
example config added
2022-08-24 13:00:55 +02:00
