README.md

metadata

tags:
  - Pixelcopter-PLE-v0
  - ppo
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
  - deep-rl-course
model-index:
  - name: SARSA_QLEARNING
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Pixelcopter-PLE-v0
          type: Pixelcopter-PLE-v0
        metrics:
          - type: mean_reward
            value: 49.30 +/- 37.85
            name: mean_reward
            verified: false

REINFORCE Agent Playing Pixelcopter-PLE-v0

This is a trained model of a REINFORCE agent playing Pixelcopter-PLE-v0.

Hyperparameters

hp_seed: 1
hp_torch_deterministic: True
hp_nb_frames: 8
hp_total_timesteps: 1005000
hp_learning_t: 500
hp_num_envs: 12
hp_learning_rate: 0.0001
hp_gamma: 0.99
hp_buffer_size: 10000
hp_batch_size: 32