proyrb/ppo-LunarLander-v2

PPO Agent Playing LunarLander-v2

  This is a trained model of a PPO agent playing LunarLander-v2.
  ## Evaluation Results
  - Mean Reward: -56.14 ± 76.83
  - Number of Evaluation Episodes: 10
  ## Hyperparameters
  ```python
  {'env_id': 'LunarLander-v2'

'total_timesteps': 100000 'learning_rate': 0.0003 'num_envs': 8 'num_steps': 2048 'update_epochs': 10 'num_minibatches': 32 'clip_coef': 0.5 'seed': 136 'repo_id': 'proyrb/ppo-LunarLander-v2' 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'norm_adv': True 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'batch_size': 16384 'minibatch_size': 512}