Lunar lander with reinforcement learning

This is a NeuroMatch Academy Project:

  • using an internal physical model (in general, any causal model) to do planning;
  • obstacle avoidance with transfer learning.

Code at: https://doi.org/10.5281/zenodo.5245166 (yes, you need a DOI for toy code)

reinforcement learning framework

Reference:

[1] Sutton, R.S. and Barto, A.G., 2018. Reinforcement learning: An introduction. MIT press.
[2] Gou, S.Z. and Liu, Y., 2019. DQN with model-based exploration: efficient learning on environments with sparse rewards. arXiv preprint arXiv:1903.09295.