Erni 1aee41fa9c

Using dist.mode instead of logits.argmax (#1066) ...

changed all the occurrences where an action is selected deterministically

- **from**: using the outputs of the actor network.
- **to**: using the mode of the PyTorch distribution.

---------

Co-authored-by: Arnau Jimenez <arnau.jimenez@zeiss.com>

2024-03-03 00:09:39 +01:00

..

base

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

continuous

Using dist.mode instead of logits.argmax (#1066)

2024-03-03 00:09:39 +01:00

discrete

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

highlevel

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

modelbased

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

offline

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

pettingzoo

Refactoring/mypy issues test (#1017)

2024-02-06 14:24:30 +01:00

__init__.py

add test_buffer

2020-03-11 17:28:51 +08:00