Richard Jozsa
cd5016d0c7
Merge branch 'freqtrade:feat/freqai-rl-dev' into feat/freqai-rl-dev
2022-11-22 09:47:27 +01:00
robcaulk
60fcd8dce2
fix skipped mac test, fix RL bug in add_state_info, fix use of __import__, revise doc
2022-11-17 21:50:02 +01:00
richardjozsa
ad56c45ecd
Add total profit to the monitor file and add monitor for the trainingf
...
This can help for beginners to see what is happening inside of the training, and helps them understand how much profit of their agent did under the period of training and eval.
2022-11-15 10:43:28 +01:00
richardjozsa
926f870fb5
Improve the training by randomly setting the starting point
...
This is an improvement for all kind of RL stuff, the starting point sets in the first third of the data which ensures that the model not only optimizes the policy or Q values to the choosen timerange.
2022-11-15 00:16:04 +01:00
robcaulk
6394ef4558
fix docstrings
2022-11-13 17:43:52 +01:00
robcaulk
388ca21200
update docs, fix bug in environment
2022-11-13 16:56:31 +01:00
robcaulk
af9e400562
add test coverage, fix bug in base environment. Ensure proper fee is used.
2022-11-13 15:31:37 +01:00
robcaulk
81f800a79b
switch to using FT calc_profi_pct, reverse entry/exit fees
2022-11-13 13:41:17 +01:00
robcaulk
e71a8b8ac1
add ability to integrate state info or not, and prevent state info integration during backtesting
2022-11-12 18:46:48 +01:00
robcaulk
9c6b97c678
ensure normalization acceleration methods are employed in RL
2022-11-12 12:01:59 +01:00
robcaulk
6746868ea7
store dataprovider to self instead of strategy
2022-11-12 11:33:03 +01:00
robcaulk
8d7adfabe9
clean RL tests to avoid dir pollution and increase speed
2022-10-08 12:10:38 +02:00
robcaulk
488739424d
fix reward inconsistency in template
2022-10-05 20:55:50 +02:00
robcaulk
cf882fa84e
fix tests
2022-10-01 20:26:41 +02:00
Robert Caulk
555cc42630
Ensure 1 thread is available (for testing purposes)
2022-09-29 14:00:09 +02:00
Robert Caulk
dcf6ebe273
Update BaseReinforcementLearningModel.py
2022-09-29 00:37:03 +02:00
robcaulk
83343dc2f1
control number of threads, update doc
2022-09-29 00:10:18 +02:00
robcaulk
647200e8a7
isort
2022-09-23 19:30:56 +02:00
robcaulk
77c360b264
improve typing, improve docstrings, ensure global tests pass
2022-09-23 19:17:27 +02:00
Robert Caulk
f5cd8f62c6
Remove unused code from BaseEnv
2022-09-23 10:24:39 +02:00
robcaulk
7295ba0fb2
add test for Base4ActionEnv
2022-09-22 23:42:33 +02:00
robcaulk
eeebb78a5c
skip darwin in RL tests, remove example scripts, improve doc
2022-09-22 21:16:21 +02:00
robcaulk
7b1d409c98
fix mypy/flake8
2022-09-17 17:51:06 +02:00
robcaulk
3b97b3d5c8
fix mypy error for strategy
2022-09-15 00:56:51 +02:00
robcaulk
8aac644009
add tests. add guardrails.
2022-09-15 00:46:35 +02:00
robcaulk
48140bff91
fix bug in 4ActRLEnv
2022-09-14 22:53:53 +02:00
robcaulk
27dce20b29
fix bug in Base4ActionRLEnv, improve example strats
2022-09-04 11:21:54 +02:00
Richard Jozsa
2493e0c8a5
Unnecessary lines in Base4, and changes for box space, to fit better for our needs ( #7324 )
2022-08-31 16:37:02 +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
robcaulk
baa4f8e3d0
remove Base3ActionEnv in favor of Base4Action
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
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
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
