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/blob/release_13_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_14_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.
* C# implementation catered toward a Match-3 setup including concepts around encoding for moves based on [Human Like Playtesting with Deep Learning](https://www.researchgate.net/publication/328307928_Human-Like_Playtesting_with_Deep_Learning)
* An example Match-3 scene with ML-Agents implemented (located under /Project/Assets/ML-Agents/Examples/Match3). More information, on Match-3 example [here](https://github.com/Unity-Technologies/ml-agents/tree/release_13_docs/docs/docs/Learning-Environment-Examples.md#match-3).
* An example Match-3 scene with ML-Agents implemented (located under /Project/Assets/ML-Agents/Examples/Match3). More information, on Match-3 example [here](https://github.com/Unity-Technologies/ml-agents/tree/release_14_docs/docs/docs/Learning-Environment-Examples.md#match-3).
### Feedback
If you are a Match-3 developer and are trying to leverage ML-Agents for this scenario, [we want to hear from you](https://forms.gle/TBsB9jc8WshgzViU9). Additionally, we are also looking for interested Match-3 teams to speak with us for 45 minutes. If you are interested, please indicate that in the [form](https://forms.gle/TBsB9jc8WshgzViU9). If selected, we will provide gift cards as a token of appreciation.
[Clone the repository](https://github.com/Unity-Technologies/ml-agents/tree/release_13_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_13_docs/docs/Installation.md#advanced-local-installation-for-development-1)
[Clone the repository](https://github.com/Unity-Technologies/ml-agents/tree/release_14_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_14_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.
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.
## Requirements
- No way to customize the action space of the `InputActuatorComponent`
## Need Help?
The main [README](https://github.com/Unity-Technologies/ml-agents/tree/release_13_docs/README.md) contains links for contacting the team or getting support.
The main [README](https://github.com/Unity-Technologies/ml-agents/tree/release_14_docs/README.md) contains links for contacting the team or getting support.
/// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_13_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
/// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_14_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
One of the first decisions you need to make regarding your training run is which
trainer to use: PPO or SAC. There are some training configurations that are
trainer to use: PPO, SAC, or POCA. There are some training configurations that are
| `trainer_type` | (default = `ppo`) The type of trainer to use: `ppo` or `sac` |
| `trainer_type` | (default = `ppo`) The type of trainer to use: `ppo`, `sac`, or `poca`. |
| `summary_freq` | (default = `50000`) Number of experiences that needs to be collected before generating and displaying training statistics. This determines the granularity of the graphs in Tensorboard. |
| `time_horizon` | (default = `64`) How many steps of experience to collect per-agent before adding it to the experience buffer. When this limit is reached before the end of an episode, a value estimate is used to predict the overall expected reward from the agent's current state. As such, this parameter trades off between a less biased, but higher variance estimate (long time horizon) and more biased, but less varied estimate (short time horizon). In cases where there are frequent rewards within an episode, or episodes are prohibitively large, a smaller number can be more ideal. This number should be large enough to capture all the important behavior within a sequence of an agent's actions. <br><br> Typical range: `32` - `2048` |
| `max_steps` | (default = `500000`) Total number of steps (i.e., observation collected and action taken) that must be taken in the environment (or across all environments if using multiple in parallel) before ending the training process. If you have multiple agents with the same behavior name within your environment, all steps taken by those agents will contribute to the same `max_steps` count. <br><br>Typical range: `5e5` - `1e7` |
| `network_settings -> hidden_units` | (default = `128`) Number of units in the hidden layers of the neural network. Correspond to how many units are in each fully connected layer of the neural network. For simple problems where the correct action is a straightforward combination of the observation inputs, this should be small. For problems where the action is a very complex interaction between the observation variables, this should be larger. <br><br> Typical range: `32` - `512` |
| `network_settings -> num_layers` | (default = `2`) The number of hidden layers in the neural network. Corresponds to how many hidden layers are present after the observation input, or after the CNN encoding of the visual observation. For simple problems, fewer layers are likely to train faster and more efficiently. More layers may be necessary for more complex control problems. <br><br> Typical range: `1` - `3` |
| `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. |
| `network_settings -> vis_encoder_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 is optimized for board games, and can be used down to visual observation sizes of 5x5. |
| `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 is optimized for board games, and can be used down to visual observation sizes of 5x5. |
## Trainer-specific Configurations
| `hyperparameters -> tau` | (default = `0.005`) How aggressively to update the target network used for bootstrapping value estimation in SAC. Corresponds to the magnitude of the target Q update during the SAC model update. In SAC, there are two neural networks: the target and the policy. The target network is used to bootstrap the policy's estimate of the future rewards at a given state, and is fixed while the policy is being updated. This target is then slowly updated according to tau. Typically, this value should be left at 0.005. For simple problems, increasing tau to 0.01 might reduce the time it takes to learn, at the cost of stability. <br><br>Typical range: `0.005` - `0.01` |
| `hyperparameters -> steps_per_update` | (default = `1`) Average ratio of agent steps (actions) taken to updates made of the agent's policy. In SAC, a single "update" corresponds to grabbing a batch of size `batch_size` from the experience replay buffer, and using this mini batch to update the models. Note that it is not guaranteed that after exactly `steps_per_update` steps an update will be made, only that the ratio will hold true over many steps. Typically, `steps_per_update` should be greater than or equal to 1. Note that setting `steps_per_update` lower will improve sample efficiency (reduce the number of steps required to train) but increase the CPU time spent performing updates. For most environments where steps are fairly fast (e.g. our example environments) `steps_per_update` equal to the number of agents in the scene is a good balance. For slow environments (steps take 0.1 seconds or more) reducing `steps_per_update` may improve training speed. We can also change `steps_per_update` to lower than 1 to update more often than once per step, though this will usually result in a slowdown unless the environment is very slow. <br><br>Typical range: `1` - `20` |
| `hyperparameters -> reward_signal_num_update` | (default = `steps_per_update`) Number of steps per mini batch sampled and used for updating the reward signals. By default, we update the reward signals once every time the main policy is updated. However, to imitate the training procedure in certain imitation learning papers (e.g. [Kostrikov et. al](http://arxiv.org/abs/1809.02925), [Blondé et. al](http://arxiv.org/abs/1809.02064)), we may want to update the reward signal (GAIL) M times for every update of the policy. We can change `steps_per_update` of SAC to N, as well as `reward_signal_steps_per_update` under `reward_signals` to N / M to accomplish this. By default, `reward_signal_steps_per_update` is set to `steps_per_update`. |
### MA-POCA-specific Configurations
MA-POCA uses the same configurations as PPO, and there are no additional POCA-specific parameters.
**NOTE**: Reward signals other than Extrinsic Rewards have not been extensively tested with MA-POCA,
though they can still be added and used for training on a your-mileage-may-vary basis.
GitHub
4 年前
