README.md

metadata

tags:
  - LunarLander-v2
  - ppo
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
  - deep-rl-course
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: '-101.69 +/- 95.52'
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2.

Hyperparameters

{'max_frames': 400000
'gamma': 0.95
'PPO_epsilon': 0.2
'max_t': 99
'target_nets_update_freq': 50
'lr': 0.00025
'entropy_coef': 0.01
'env_id': 'LunarLander-v2'}