Skip to content

Commit 961876b

Browse files
Removed mention of release 19 (#5637)
* Removed mention of release 19 * revert release 19 doc changes Co-authored-by: mahon94 <maryam.honari@unity3d.com>
1 parent d9b493a commit 961876b

File tree

3 files changed

+0
-7
lines changed

3 files changed

+0
-7
lines changed

docs/Getting-Started.md

Lines changed: 0 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -119,9 +119,6 @@ example.
119119
**Note** : You can modify multiple game objects in a scene by selecting them
120120
all at once using the search bar in the Scene Hierarchy.
121121
1. Set the **Inference Device** to use for this model as `CPU`.
122-
1. If the model is trained with Release 19 or later, you can select
123-
`Deterministic Inference` to choose actions deterministically from the model.
124-
Works only for inference within unity with no python process involved.
125122
1. Click the **Play** button in the Unity Editor and you will see the platforms
126123
balance the balls using the pre-trained model.
127124

docs/Learning-Environment-Design-Agents.md

Lines changed: 0 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -987,9 +987,6 @@ be called independently of the `Max Step` property.
987987
training)
988988
- `Inference Device` - Whether to use CPU or GPU to run the model during
989989
inference
990-
- `Deterministic Inference` - Weather to set action selection to deterministic,
991-
Only applies to inference from within unity (with no python process involved) and
992-
Release 19 or later.
993990
- `Behavior Type` - Determines whether the Agent will do training, inference,
994991
or use its Heuristic() method:
995992
- `Default` - the Agent will train if they connect to a python trainer,

docs/Training-Configuration-File.md

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,6 @@ choice of the trainer (which we review on subsequent sections).
4444
| `network_settings -> normalize` | (default = `false`) Whether normalization is applied to the vector observation inputs. This normalization is based on the running average and variance of the vector observation. Normalization can be helpful in cases with complex continuous control problems, but may be harmful with simpler discrete control problems. |
4545
| `network_settings -> vis_encode_type` | (default = `simple`) Encoder type for encoding visual observations. <br><br> `simple` (default) uses a simple encoder which consists of two convolutional layers, `nature_cnn` uses the CNN implementation proposed by [Mnih et al.](https://www.nature.com/articles/nature14236), consisting of three convolutional layers, and `resnet` uses the [IMPALA Resnet](https://arxiv.org/abs/1802.01561) consisting of three stacked layers, each with two residual blocks, making a much larger network than the other two. `match3` is a smaller CNN ([Gudmundsoon et al.](https://www.researchgate.net/publication/328307928_Human-Like_Playtesting_with_Deep_Learning)) that can capture more granular spatial relationships and is optimized for board games. `fully_connected` uses a single fully connected dense layer as encoder without any convolutional layers. <br><br> Due to the size of convolution kernel, there is a minimum observation size limitation that each encoder type can handle - `simple`: 20x20, `nature_cnn`: 36x36, `resnet`: 15 x 15, `match3`: 5x5. `fully_connected` doesn't have convolutional layers and thus no size limits, but since it has less representation power it should be reserved for very small inputs. Note that using the `match3` CNN with very large visual input might result in a huge observation encoding and thus potentially slow down training or cause memory issues. |
4646
| `network_settings -> conditioning_type` | (default = `hyper`) Conditioning type for the policy using goal observations. <br><br> `none` treats the goal observations as regular observations, `hyper` (default) uses a HyperNetwork with goal observations as input to generate some of the weights of the policy. Note that when using `hyper` the number of parameters of the network increases greatly. Therefore, it is recommended to reduce the number of `hidden_units` when using this `conditioning_type`
47-
| `network_settings -> deterministic` | (default = `false`) When set to true, ensures that actions are selected from the models output deterministically to ensure predictable and reproducible results. This can be overwritten by the `--deterministic` flag on the CLI.
4847

4948

5049
## Trainer-specific Configurations

0 commit comments

Comments
 (0)