129 Commits

Author	SHA1	Message	Date
robcaulk	d8565261e1	ignore initializer type	2022-12-04 14:10:33 +01:00
robcaulk	24766928ba	reorganize/generalize tensorboard callback	2022-12-04 13:54:30 +01:00
smarmau	b2edc58089	fix flake8	2022-12-03 22:31:02 +11:00
smarmau	469aa0d43f	add state/action info to callbacks	2022-12-03 21:16:46 +11:00
Matthias	4dc591a170	Merge pull request #7834 from freqtrade/fix-data-drawer-model-load ... Fix sb3_contrib loading issue	2022-12-02 06:29:23 +01:00
robcaulk	2b3e166dc2	fix fees RL	2022-12-01 10:10:28 +01:00
Emre	4a9982f86b	Fix sb3_contrib loading issue	2022-12-01 10:08:42 +03:00
robcaulk	e7f72d52b8	bring back market side setting in get_state_info	2022-11-30 12:36:26 +01:00
Matthias	c3daddc629	Merge pull request #7809 from richardjozsa/develop ... Improve the RL learning process	2022-11-29 06:28:36 +01:00
Emre	9cbfa12011	Directly set model_type in base RL model	2022-11-28 16:02:17 +03:00
robcaulk	56518def42	isort	2022-11-27 21:06:01 +01:00
robcaulk	7fd6bc526e	add randomize_starting_position to the rl_config	2022-11-27 21:03:13 +01:00
richardjozsa	64d4a52a56	Improve the RL learning process ... Improve the RL learning process by selecting random start point for the agent, it can help to block the agent to only learn on the selected period of time, while improving the quality of the model.	2022-11-27 20:43:50 +01:00
stm	51d21b413d	Fix 4ac update_total_profit ... _update_total_profit() must be executed before "self._position = Positions.Neutral" because _update_total_profit() calls get_unrealized_profit(), which returns 0 if position is neutral and total_profit is not updated	2022-11-26 23:35:20 +03:00
robcaulk	be890b52fd	remove np import	2022-11-26 13:44:58 +01:00
robcaulk	aaaa5a5f64	add documentation for net_arch, other small changes	2022-11-26 13:44:58 +01:00
Matthias	7ebc8ee169	Fix missing Optional typehint	2022-11-26 13:32:18 +01:00
Matthias	bdfedb5fcb	Improve typehints / reduce warnings from mypy	2022-11-26 13:03:07 +01:00
robcaulk	81fd2e588f	ensure typing, remove unsued code	2022-11-26 12:11:59 +01:00
robcaulk	3a07749fcc	fix docstring	2022-11-24 18:46:54 +01:00
robcaulk	44b042ba51	remove unused function	2022-11-24 17:53:26 +01:00
Matthias	8f1a8c752b	Add freqairl docker build process	2022-11-24 07:00:12 +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
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
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
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
sonnhfit	0475b7cb18	remove unuse code and fix coding conventions	2022-08-24 13:00:55 +02:00
robcaulk	bf7ceba958	set cpu threads in config	2022-08-24 13:00:55 +02:00
robcaulk	acf3484e88	add multiprocessing variant of ReinforcementLearningPPO	2022-08-24 13:00:55 +02:00
robcaulk	926023935f	make base 3ac and base 5ac environments. TDQN defaults to 3AC.	2022-08-24 13:00:55 +02:00
robcaulk	91683e1dca	restructure RL so that user can customize environment	2022-08-24 13:00:55 +02:00