LunarLander-v2 ppo deep-reinforcement-learning reinforcement-learning custom-implementation deep-rl-course

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'exp_name': 'LunarLander-v3'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'f': '/root/.local/share/jupyter/runtime/kernel-b1e556d7-bdda-4e73-8875-1705f0553981.json'
'env_id': 'LunarLander-v2'
'total_timesteps': 1000000
'learning_rate': 0.002
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.88
'num_minibatches': 8
'update_epochs': 3
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.0009
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'mgmeskill/ppo-LunarLander-v3'
'batch_size': 512
'minibatch_size': 64}