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: 283.68 +/- 23.30
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'env_id': 'LunarLander-v2'
'learning_rate': 0.0007
'gamma': 0.98
'gae_lambda': 0.95
'clip_coef': 0.2
'total_timesteps': 50000000
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'epsilon': 0.01
'num_minibatches': 4
'update_epochs': 4}