metadata

tags:
  - MountainCarContinuous-v0
  - a2c
  - reinforcement-learning
  - custom-implementation
model-index:
  - name: A2C-MountainCarContinuous-v0
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: MountainCarContinuous-v0
          type: MountainCarContinuous-v0
        metrics:
          - type: mean_reward
            value: 90.98 +/- 3.32
            name: mean_reward
            verified: false

A2C Agent playing MountainCarContinuous-v0

Custom A2C model with a frameskip that solves the MountainCarContinuous-v0 env. Training and usage details are in the 2.1 A2C_on_MountainCarContinuous-v0_frameskip.ipynb jupyter notebook file.

Training progress:

In case video demo does not show on the model card, here's a gif: