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: '-157.06 +/- 48.98'
            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'
'n_envs': 8
'n_steps': 128
'epochs': 4
'lr': 1e-05
'gamma': 0.99
'n_minibatches': 4
'batch_size': 1024
'minibatch_size': 256
'total_timesteps': 10000000
'n_iterations': 9765
'norm_adv': True
'epsilon': 0.2
'clip_vloss': True
'vf_coef': 0.5
'ent_coef': 0.01}