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: '-26.75 +/- 72.19'
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'seed': 1
'env_id': 'LunarLander-v2'
'total_timesteps': 100000
'num_envs': 8
'num_steps': 128
'gamma': 0.99
'gae_lambda': 0.95
'learning_rate': 0.0003
'clip_range': 0.2
'value_loss_coef': 0.5
'entropy_loss_coef': 0.01
'max_grad_norm': 0.5
'update_epochs': 4
'mini_batch_size': 64
'eval_freq': 10
'no_cuda': False
'repo_id': 'jrauch/ppo-{env}'}