| {"exp_name": "ppo", | |
| "seed": 1, | |
| "wandb_project_name": "cleanRL", | |
| "env_id": "LunarLander-v2", | |
| "total_timesteps": 2000000, | |
| "learning_rate": 0.00035, | |
| "num_envs": 4, | |
| "num_steps": 1024, | |
| "gamma": 0.999, | |
| "gae_lambda": 0.98, | |
| "num_minibatches": 4, | |
| "update_epochs": 4, | |
| "clip_coef": 0.2, | |
| "ent_coef": 0.01, | |
| "vf_coef": 0.5, | |
| "max_grad_norm": 0.5, | |
| "repo_id": "pableitorr/LunarLander-v2-UNIT8", | |
| "batch_size": 4096, | |
| "minibatch_size": 1024} |