An image can be thought of as a matrix of a predefined width (W) and a height (H) and each pixel can be thought of as simply an array of length 3 (in the case of RGB), `[Red, Green, Blue]` holding the different channel information of the color (channel) intensities at that pixel location. Thus an image is just a 3 dimensional matrix of size WxHx3. A Grid Observation can be thought of as a generalization of this setup where in place of a pixel there is a "cell" which is an array of length N representing different channel intensities at that cell position. From a Convolutional Neural Network point of view, the introduction of multiple channels in an "image" isn't a new concept. One such example is using an RGB-Depth image which is used in several robotics applications. The distinction of Grid Observations is what the data within the channels represents. Instead of limiting the channels to color intensities, the channels within a cell of a Grid Observation generalize to any data that can be represented by a single number (float or int).
Before jumping into the details of the Grid Sensor, an important thing to note is the agent performance and qualitatively different behavior over raycasts. Unity MLAgent's comes with a suite of example environments. One in particular, the [Food Collector](https://github.com/Unity-Technologies/ml-agents/tree/release_15_docs/docs/Learning-Environment-Examples.md#food-collector), has been the focus of the Grid Sensor development.
Before jumping into the details of the Grid Sensor, an important thing to note is the agent performance and qualitatively different behavior over raycasts. Unity MLAgent's comes with a suite of example environments. One in particular, the [Food Collector](https://github.com/Unity-Technologies/ml-agents/tree/release_16_docs/docs/Learning-Environment-Examples.md#food-collector), has been the focus of the Grid Sensor development.
The Food Collector environment can be described as:
* Set-up: A multi-agent environment where agents compete to collect food.
[Clone the repository](https://github.com/Unity-Technologies/ml-agents/tree/release_15_docs/docs/Installation.md#clone-the-ml-agents-toolkit-repository-optional) and follow the
[Local Installation for Development](https://github.com/Unity-Technologies/ml-agents/tree/release_15_docs/docs/Installation.md#advanced-local-installation-for-development-1)
[Clone the repository](https://github.com/Unity-Technologies/ml-agents/tree/release_16_docs/docs/Installation.md#clone-the-ml-agents-toolkit-repository-optional) and follow the
[Local Installation for Development](https://github.com/Unity-Technologies/ml-agents/tree/release_16_docs/docs/Installation.md#advanced-local-installation-for-development-1)
See [Git dependencies](https://docs.unity3d.com/Manual/upm-git.html#subfolder) for more information. Note that this
may take several minutes to resolve the packages the first time that you add it.
- No way to customize the action space of the `InputActuatorComponent`
## Need Help?
The main [README](https://github.com/Unity-Technologies/ml-agents/tree/release_15_docs/README.md) contains links for contacting the team or getting support.
The main [README](https://github.com/Unity-Technologies/ml-agents/tree/release_16_docs/README.md) contains links for contacting the team or getting support.
- The `.onnx` models input names have changed. All input placeholders will now use the prefix `obs_` removing the distinction between visual and vector observations. In addition, the inputs and outputs of LSTM changed. Models created with this version will not be usable with previous versions of the package (#5080, #5236)
settings. Unfortunately, this may require retraining models if it changes the resulting order of the sensors
or actuators on your system. (#5194)
- Removed additional memory allocations that were occurring due to assert messages and iterating of DemonstrationRecorders. (#5246)
- Fixed erroneous warnings when using the Demonstration Recorder. (#5216)
- ELO now correctly resumes when loading from a checkpoint. (#5202)
- In the Python API, fixed `validate_action` to expect the right dimensions when `set_action_single_agent` is called. (#5208)
- In the `GymToUnityWrapper`, raise an appropriate warning if `step()` is called after an environment is done. (#5204)
- Fixed an issue where using one of the `gym` wrappers would override user-set log levels. (#5201)
## [1.9.0-preview] - 2021-03-17
### Major Changes
#### com.unity.ml-agents (C#)
- Added a `--torch-device` commandline option to `mlagents-learn`, which sets the default
[`torch.device`](https://pytorch.org/docs/stable/tensor_attributes.html#torch.torch.device) used for training. (#4888)
- The `--cpu` commandline option had no effect and was removed. Use `--torch-device=cpu` to force CPU training. (#4888)
- The `mlagents_env` API has changed, `BehaviorSpec` now has a `observation_specs` property containing a list of `ObservationSpec`. For more information on `ObservationSpec` see [here](https://github.com/Unity-Technologies/ml-agents/blob/main/docs/Python-API.md#behaviorspec). (#4763, #4825)
- The `mlagents_env` API has changed, `BehaviorSpec` now has a `observation_specs` property containing a list of `ObservationSpec`. For more information on `ObservationSpec` see [here](https://github.com/Unity-Technologies/ml-agents/blob/release_13_docs/docs/Python-API.md#behaviorspec). (#4763, #4825)
[installation docs](https://github.com/Unity-Technologies/ml-agents/blob/main/docs/Installation.md) for
[installation docs](https://github.com/Unity-Technologies/ml-agents/blob/release_10_docs/docs/Installation.md) for
more information on installing PyTorch. For the time being, TensorFlow is still available;
you can use the TensorFlow backend by adding `--tensorflow` to the CLI, or
adding `framework: tensorflow` in the configuration YAML. (#4517)
- The Barracuda dependency was upgraded to 1.1.2 (#4571)
- Utilities were added to `com.unity.ml-agents.extensions` to make it easier to
integrate with match-3 games. See the [readme](https://github.com/Unity-Technologies/ml-agents/blob/main/com.unity.ml-agents.extensions/Documentation~/Match3.md)
integrate with match-3 games. See the [readme](https://github.com/Unity-Technologies/ml-agents/blob/release_10_docs/com.unity.ml-agents.extensions/Documentation~/Match3.md)
- The Parameter Randomization feature has been refactored to enable sampling of new parameters per episode to improve robustness. The
`resampling-interval` parameter has been removed and the config structure updated. More information [here](https://github.com/Unity-Technologies/ml-agents/blob/main/docs/Training-ML-Agents.md). (#4065)
`resampling-interval` parameter has been removed and the config structure updated. More information [here](https://github.com/Unity-Technologies/ml-agents/blob/release_5_docs/docs/Training-ML-Agents.md). (#4065)
/// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_15_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
/// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_16_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
GitHub
4 年前