Liapunov/ppo-scratch-LunarLander-v2

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'total_timesteps': 500000, 'learning_rate': 1e-05, 'num_envs': 1, 'num_steps': 256, 'anneal_lr': True, 'gae': True, 'gamma': 0.99, 'gae_lambda': 0.95, 'num_minibatches': 4, 'update_epochs': 4, 'norm_adv': True, 'clip_coef': 0.2, 'clip_vloss': True, 'ent_coef': 0, 'vf_coef': 0, 'max_grad_norm': 0.5, 'target_kl': None, 'batch_size': 256, 'minibatch_size': 64, 'env_id': 'LunarLander-v2', 'name': 'ppo', 'seed': 1, 'torch_deterministic': False, 'cuda': False, 'track': False, 'wandb_project_name': 'dirtyRL', 'wandb_entity': None, 'capture_video': False, 'repo_id': 'Liapunov/ppo-scratch-LunarLander-v2'}