Skip to content
Snippets Groups Projects
Select Git revision
  • 7b95127fd2085ff7b9ff2a61a7ee627972abfd77
  • master default protected
2 results

TD06

  • Clone with SSH
  • Clone with HTTPS
  • Hands-on Reinforcement Learning

    MOREAU Maxime, 3A - Computer science & M2 DS, ECL22

    1. RL for CartPole-v1

    1.1 Training

    1.2 Evaluation

    We finally have an evaluation with 100% of sucess:

    alt text

    2. Complete RL pipeline to solve CartPole environment with A2C.

    Here we set up a complete pipeline to solve Cartpole environment with A2C algorithm.

    Wandb has been set up to follow the learning phase. https://wandb.ai/maximecerise-ecl/cartpole-a2c alt text