PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'exp_name': 'ppo'
'env_id': 'LunarLander-v2'
'seed': 1
'total_timesteps': 100000
'learning_rate': 0.00025
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'norm_adv': True
'clip_vloss': True
'cuda': True
'torch_deterministic': False
'track': False
'wandb_project_name': None
'wandb_entity': None
'num_envs': 4
'num_steps': 128
'capture_video': False
'num_minibatches': 4
'update_epochs': 4
'clip_coef': 0.2
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'push_to_huggingface': 'alexeynoskov/ppo-LunarLander-v2-cleanrl'
'batch_size': 512
'minibatch_size': 128}