|
---
|
|
tags:
|
|
- CartPole-v1
|
|
- reinforcement-learning
|
|
- rl-framework
|
|
model-index:
|
|
- name: Test_Imitation_Again_Cartpole
|
|
results:
|
|
- task:
|
|
type: reinforcement-learning
|
|
name: reinforcement-learning
|
|
dataset:
|
|
name: CartPole-v1
|
|
type: CartPole-v1
|
|
metrics:
|
|
- type: mean_reward
|
|
value: 37.82 +/- 27.02
|
|
name: mean_reward
|
|
verified: false
|
|
---
|
|
|
|
|
|
# Custom implemented BC agent playing on *CartPole-v1*
|
|
|
|
This is a trained model of an agent playing on the environment *CartPole-v1*.
|
|
The agent was trained with a BC algorithm.
|
|
See further agent and evaluation metadata in the according README section.
|
|
|
|
|
|
## Import
|
|
The Python module used for training and uploading/downloading is [rl-framework](https://github.com/alexander-zap/rl-framework).
|
|
It is an easy-to-read, plug-and-use Reinforcement Learning framework and provides standardized interfaces
|
|
and implementations to various Reinforcement Learning methods and environments.
|
|
|
|
Also it provides connectors for the upload and download to popular model version control systems,
|
|
including the HuggingFace Hub.
|
|
|
|
## Usage
|
|
```python
|
|
|
|
from rl-framework import ImitationAgent, ImitationAlgorithm
|
|
|
|
# Create new agent instance
|
|
agent = ImitationAgent(
|
|
algorithm=ImitationAlgorithm.BC
|
|
algorithm_parameters={
|
|
...
|
|
},
|
|
)
|
|
|
|
# Download existing agent from HF Hub
|
|
repository_id = "zap-thamm/Test_Imitation_Again_Cartpole"
|
|
file_name = "agent.zip"
|
|
agent.download(repository_id=repository_id, filename=file_name)
|
|
|
|
```
|
|
|
|
Further examples can be found in the [exploration section of the rl-framework repository](https://github.com/alexander-zap/rl-framework/tree/main/exploration).
|
|
|
|
|
