Commit Graph

569 Commits

Author SHA1 Message Date
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
Matthias
f4025ee5de
Merge pull request #7289 from freqtrade/feat/freqai-rl-dev
Add reinforcement learning module to FreqAI
2022-11-27 17:15:21 +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
dba30393fb ensure extra_returns_per_train are set properly on first hist_preds build 2022-11-26 18:04:47 +01:00
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
8dbfd2cacf improve docstring clarity about how to inherit from ReinforcementLearner, demonstrate inherittance with ReinforcementLearner_multiproc 2022-11-26 11:51:08 +01:00
robcaulk
2e82e6784a move data_provider cleanup to shutdown() 2022-11-24 19:07:38 +01:00
robcaulk
73c458d47b use importlib instead of __import___ 2022-11-24 19:04:35 +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
387c905a86 merge develop into RL 2022-11-17 21:59:07 +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
Robert Caulk
cd6f87be17
Merge pull request #7728 from freqtrade/improve_timerange
Simplify timerange handling
2022-11-17 19:57:48 +01:00
robcaulk
bf4d5b432a ensure model_type is defined 2022-11-13 18:50:25 +01:00
robcaulk
6394ef4558 fix docstrings 2022-11-13 17:43:52 +01:00
robcaulk
96fafb7f56 remove limit_ram_use 2022-11-13 17:14:47 +01:00
robcaulk
b421521be3 help default ReinforcementLearner users by assigning the model_type automatically 2022-11-13 17:12:17 +01:00
robcaulk
90f168d1ff remove more user references. cleanup dataprovider 2022-11-13 17:06:06 +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
Matthias
942840da2d Improve setting wording to keep future possibilities open 2022-11-13 15:22:44 +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
7a4bb040a5 merge develop into feat/freqai-rl-dev 2022-11-12 10:54:34 +01:00
robcaulk
214c622475 move dataframe converter to converter.py 2022-11-12 10:38:25 +01:00
robcaulk
9617d8143d Merge remote-tracking branch 'origin/develop' into add-single-precision-freqai 2022-11-12 10:21:38 +01:00
Matthias
e6172a68d7
Merge pull request #7730 from freqtrade/fix-metric-tracker
fix loading of metric tracker from disk
2022-11-11 20:01:26 +01:00
Robert Caulk
833578716c
Merge pull request #7644 from markdregan/multi-target-classifier
Support for multi target multi-class classification (FreqaiMultiOutputRegressor for Classification)
2022-11-11 18:48:38 +01:00
robcaulk
790ff2a84b merge develop into add-single-prec 2022-11-11 18:08:51 +01:00
robcaulk
e46a57bbd0 move mem logs to debug 2022-11-11 18:05:32 +01:00
robcaulk
66514e84e4 add LightGBMClassifierMultiTarget. add test 2022-11-11 17:45:53 +01:00
robcaulk
054133955b fix loading of metric tracker from disk 2022-11-11 17:24:09 +01:00
Matthias
0f9c5f8d41 Simplify timerange handling 2022-11-10 18:28:18 +01:00
Matthias
57313dd961 Update some usages of timerange to new, simplified method 2022-11-10 18:11:39 +01:00
Matthias
884014a4b9 Fix some minor typos 2022-11-07 18:35:28 +00:00
Wagner Costa Santos
6559384286 Merge branch 'develop' into backtest_live_models 2022-11-07 15:14:10 -03:00
Emre
43bdd34964
Optimize reduce_dataframe_footprint function 2022-11-05 19:13:02 +03:00
robcaulk
53df607067 avoid duplicating features with okx/gateio, ensure inference timer gets logged 2022-11-05 15:42:19 +01:00
robcaulk
257c833831 add doc for single precision, dont allow half precision, add test 2022-11-04 18:10:04 +01:00
robcaulk
3ccc120f92 add option to force single precision 2022-11-04 17:42:10 +01:00
robcaulk
8bdc99a3d6 fix self-imposed bug 2022-11-04 16:41:38 +01:00