File tree Expand file tree Collapse file tree 2 files changed +7
-10
lines changed
com.unity.ml-agents.extensions Expand file tree Collapse file tree 2 files changed +7
-10
lines changed Original file line number Diff line number Diff line change 1
1
# Changelog
2
- All notable changes to this package will be documented in this file.
3
-
4
- The format is based on [ Keep a Changelog] ( http://keepachangelog.com/en/1.0.0/ )
5
- and this project adheres to [ Semantic Versioning] ( http://semver.org/spec/v2.0.0.html ) .
2
+ This changelog isn't used; please add to the ` com.unity.ml-agents ` changelog instead.
6
3
7
4
## [ Unreleased]
8
5
* Initial version
9
-
10
- ### Minor Changes
11
- #### com.unity.ml-agents.extensions (C#)
12
- - Added the GridSensor and GridSensor tests
13
- #### ml-agents-envs (Python)
14
- - Modified the rpc_utils.py to support multiple PNGs
Original file line number Diff line number Diff line change @@ -13,15 +13,21 @@ and this project adheres to
13
13
#### ml-agents / ml-agents-envs / gym-unity (Python)
14
14
15
15
### Minor Changes
16
+
16
17
#### com.unity.ml-agents (C#)
17
18
- Update Barracuda to 1.1.0-preview (#4208 )
18
19
- Enabled C# formatting using ` dotnet-format ` . (#4362 )
20
+ - GridSensor was added to the com.unity.ml-agents.extensions package. Thank you
21
+ to Jaden Travnik from Eidos Montreal for the contribution! (#4399 )
19
22
#### ml-agents / ml-agents-envs / gym-unity (Python)
20
23
- Experimental PyTorch support has been added. Use ` --torch ` when running ` mlagents-learn ` , or add
21
24
` framework: pytorch ` to your trainer configuration (under the behavior name) to enable it.
22
25
Note that PyTorch 1.6.0 or greater should be installed to use this feature; see
23
26
[ the PyTorch website] ( https://pytorch.org/ ) for installation instructions. (#4335 )
24
27
- The minimum supported version of TensorFlow was increased to 1.14.0. (#4411 )
28
+ - Compressed visual observations with >3 channels are now supported. In
29
+ ISensor.GetCompressedObservation(), this can be done by writing 3 channels at a
30
+ time to a PNG and concatenating the resulting bytes. (#4399 )
25
31
- A CNN (` vis_encode_type: match3 ` ) for smaller grids, e.g. board games, has been added.
26
32
(#4434 )
27
33
You can’t perform that action at this time.
0 commit comments