You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: Documents/BasicConcepts.md
+16-6Lines changed: 16 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,7 +18,6 @@ This repo provides or plans to provide following tools for game AI and machine l
18
18
19
19
4. Neural Evolution(work in progess)
20
20
* Evolve the neural network's weights using MAES instead of gradien descent.
21
-
22
21
### Other tools
23
22
1. GAN(Generative adversarial network)
24
23
* Including [Traning with Prediction to Stableize](https://www.semanticscholar.org/paper/Stabilizing-Adversarial-Nets-With-Prediction-Yadav-Shah/ec25504486d8751e00e613ca6fa64b256e3581c8).
@@ -32,11 +31,22 @@ You can fisrt go through the [vverview of Unity ML-Agents](https://github.com/Un
32
31
33
32
Assume that you are somehow familiar with Unity ML-Agents, then following will be some brief explanation of concepts/key conponents that are used in this repo.
34
33
(To be added)
35
-
* Trainer
36
-
* Model
37
-
* MEAS Optimizer
38
-
* UnityNetwork
39
-
* Agent Dependent Decision
34
+
### Trainer
35
+
The Brain in ML-Agent will communiate the with a Trainer to train the Model. We added a `CoreBrainInternalTrainable` on top of the existing core brains in ML-Agent which can communicate with our Trainers. The CoreBrainInternalTrainable works with any Monobehaviour that implement the `ITrainer` interface.
36
+
37
+
We made some Trainers for you already for specific algorithm including PPO, SupervisedLearning and Evolution Strategy.
38
+
39
+
### Model
40
+
Models are the core of our AI. You can query information including the actions giving it the observations. Also, it provides interface to train the neural network.
41
+
42
+
Trainers will ask for actions and other training related data from Models during the training, and also ask to train the neural network when enough data can be provided.
43
+
44
+
### UnityNetwork
45
+
46
+
We defined some UnityNetwork scriptable objects, where you can easily define a neural network architecture for different Models, and use them as plugin modules(thanks to Unity's Scriptable Object).
47
+
48
+
The models implemented by us usually need a network scriptable object that implement certain interface. We have already made the simple version of those network for you. However, you can also easily make your own customized network.
0 commit comments