Simple Cartpole Example
What is cartpole?
This is a classic example of a problem that reinforcement learning can solve. It's a simulation of balancing a broom upright by balancing it on your hand. The broom is the "pole" and your hand is replaced with a "cart" moving back and forth on a linear track. This simplified example works in 2 dimensions, so the cart can only move in a line back and forth, and the pole can only fall forwards or backwards, not to the sides.
Sample Cart Pole Example using SageMaker RL with base docker image containing Coach, MxNet and OpenAI Gym. This is a toy example taken from
Coach Quick Start Guide. It demonstrates how you can use the
RLEstimator from the SageMaker Python SDK in
The sample notebook demonstrates how to:
- Train a toy cart pole model from a notebook and python SDK/script mode
gifsgenerated during training.
- Move these back and forth from S3 (while running in
- Checkpoint trained model
- Run inference using checkpointed models