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'}
Evaluation results
- mean_reward on LunarLander-v2self-reported30.53 +/- 70.32