danagi 60cfc373f8
fix #98, support #99 (#102)
* Add auto alpha tuning and exploration noise for sac.
Add class BaseNoise and GaussianNoise for the concept of exploration noise.
Add new test for sac tested in MountainCarContinuous-v0,
which should benefits from the two above new feature.

* add exploration noise to collector, fix example to adapt modification

* fix #98

* enable off-policy to update multiple times in one step. (#99)
2020-06-27 21:40:09 +08:00
..
2020-04-02 08:49:19 +08:00
2020-06-27 21:40:09 +08:00
2020-06-27 21:40:09 +08:00
2020-03-28 09:43:35 +08:00
2020-03-28 09:43:35 +08:00
2020-03-28 09:43:35 +08:00
2020-03-28 13:27:01 +08:00
2020-06-27 21:40:09 +08:00

Result of Ant-v2: