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: 30.53 +/- 70.32
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'exp_name': 'PPO'
'gym_id': 'LunarLander-v2'
'seed': 1
'deterministic': False
'capture_video': False
'total_timesteps': 100000
'learning_rate': 0.00025
'lr_annealing': True
'num_envs': 4
'num_steps': 128
'gae': True
'gae_lambda': 0.95
'gamma': 0.99
'minibatch_size': 128
'epochs': 4
'clip_coef': 0.2
'value_loss_coef': 0.5
'entropy_loss_coef': 0.01
'max_grad_norm': 0.5
'repo_id': 'user87441257/my-ppo-LunarLander-v2'}