176 Commits

Author	SHA1	Message	Date
simoninithomas	c458fb33c7	Update PG and add hands-on	2023-01-02 22:37:01 +01:00
simoninithomas	e1cf375c36	Update advantages-disadvantages and policy gradient	2023-01-02 22:23:27 +01:00
simoninithomas	88fded6cf3	Update intro and what are policy based mtd	2023-01-02 22:05:36 +01:00
simoninithomas	c0c4f9b565	Add conclusion	2023-01-02 21:52:41 +01:00
simoninithomas	7bb90190c7	Update Policy Gradient	2023-01-02 21:47:33 +01:00
simoninithomas	bebb6fed17	Adding conclusion	2023-01-02 21:22:44 +01:00
simoninithomas	2d2dffd4f7	Add illustrations PG	2023-01-02 20:11:50 +01:00
simoninithomas	1197198d2b	Added policy gradient section	2023-01-02 14:43:34 +01:00
simoninithomas	c71422e59c	First draft unfinished	2023-01-01 13:23:38 +01:00
Thomas Simonini	ab8598b772	Merge pull request #168 from dario248/main ... Unit 3 Glossary	2022-12-31 21:51:20 +01:00
Thomas Simonini	bc9bb6c52f	Merge pull request #170 from HasarinduPerera/main ... Update glossary.mdx [Unit 2]	2022-12-31 21:46:20 +01:00
Thomas Simonini	e60f817254	Update conclusion	2022-12-31 21:35:06 +01:00
Thomas Simonini	f9de15477c	Replace Huggy image	2022-12-31 21:30:31 +01:00
Thomas Simonini	31105e358f	Update	2022-12-31 21:22:17 +01:00
Thomas Simonini	633639d3e7	Update	2022-12-31 21:11:47 +01:00
Thomas Simonini	45d6455cd2	Update schedule	2022-12-31 21:09:32 +01:00
Thomas Simonini	90ce3173b8	Update Unit 1 notebook	2022-12-31 21:06:20 +01:00
Thomas Simonini	6d2b2b6ae7	Update _toctree.yml	2022-12-31 20:58:56 +01:00
Thomas Simonini	9b531c3be0	Some small updates	2022-12-31 20:52:40 +01:00
Thomas Simonini	10d539f24f	Update discord101.mdx	2022-12-31 20:31:21 +01:00
Thomas Simonini	8a68a5e8dc	Update setup.mdx	2022-12-31 20:25:03 +01:00
Thomas Simonini	d48dc1ad6c	Update introduction.mdx	2022-12-31 20:23:46 +01:00
Hasarindu Perera	815ae5ba13	Update glossary.mdx ... Add Epsilon-greedy strategy and Greedy strategy.	2022-12-31 13:30:42 +05:30
Dario Paez	5a4117630b	Update _toctree.yml	2022-12-28 10:24:21 -03:00
Dario Paez	779b7e5b07	Create glossary.mdx	2022-12-28 10:22:32 -03:00
Thomas Simonini	7b61d9f813	Update bellman-equation.mdx	2022-12-20 14:20:40 +01:00
Thomas Simonini	5f66e67419	Update mc-vs-td.mdx	2022-12-20 14:06:10 +01:00
Thomas Simonini	3bdc44cd35	Update bellman-equation.mdx	2022-12-20 14:05:29 +01:00
Thomas Simonini	beaef9b0a4	Update two-types-value-based-methods.mdx	2022-12-20 14:02:46 +01:00
Thomas Simonini	31dc00a52b	Update additional-readings.mdx ... Add make your own gym custom env	2022-12-20 13:59:12 +01:00
Thomas Simonini	630b80a00f	Update hands-on.mdx	2022-12-20 13:54:08 +01:00
Thomas Simonini	093bdb1ed8	Merge pull request #137 from ramon-rd/patch-1 ... Create glossary.mdx	2022-12-20 13:07:07 +01:00
Thomas Simonini	a37804cebf	Update glossary.mdx	2022-12-20 13:06:31 +01:00
Thomas Simonini	c275b13ddf	Update _toctree.yml	2022-12-20 13:04:35 +01:00
Thomas Simonini	f354d80e8c	Merge pull request #108 from huggingface/ThomasSimonini/Unit3 ... Adding Unit 3: Deep Q-Learning and Optuna Bonus	2022-12-19 16:03:11 +01:00
Thomas Simonini	fd710896cf	Update hands-on.mdx ... - Add cleanrl link - Some cleanups	2022-12-19 15:05:38 +01:00
Thomas Simonini	96b49481da	Update hands-on.mdx	2022-12-19 13:53:38 +01:00
Thomas Simonini	33c02be800	Update hands-on.mdx	2022-12-19 12:44:13 +01:00
Thomas Simonini	d500baac63	Apply suggestions from code review ... Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>	2022-12-19 12:18:26 +01:00
Andrey Voroshilov	a4cd53cd37	Fixing the reference, a) to the right Berkeley course (CS 188 and not CS 285) and b) to have a proper URL format	2022-12-18 12:24:23 -08:00
Artagon	fc66ea7e4a	Rephrasing for initial epsilon value	2022-12-17 22:33:02 +01:00
Artagon	96714cdb10	Cases consistency	2022-12-17 22:23:08 +01:00
Artagon	a7d74befb0	Fix midsentence uppercase 'Policy'	2022-12-17 14:47:18 +01:00
Artagon	753ef67eae	epsilon-greedy instead of epsilon greedy	2022-12-17 14:45:08 +01:00
Artagon	f913af7300	epsilon smaller or equal to 1.0	2022-12-17 14:39:40 +01:00
Artagon	0a4c6c6f2c	fix redundant 'pair' and inconsistent Case.	2022-12-17 14:30:19 +01:00
Artagon	0c3616c03f	Replace ** by <b> tags in figcaption	2022-12-16 20:34:24 +01:00
Artagon	0744d542ad	Properly display π*	2022-12-16 20:31:49 +01:00
Thomas Simonini	38d0b2c73a	Merge branch 'main' into ThomasSimonini/Unit3	2022-12-16 10:04:21 +01:00
simoninithomas	ed065ac128	Update Unit 3 and 4	2022-12-16 09:44:59 +01:00