LunarLander-v3-u8 / hyperparameters.json
while0628's picture
Upload PPO model, evaluation and replay
f6ca9b0 verified
Raw History Blame Contribute Delete
562 Bytes
{
"exp_name": "ppo",
"env_id": "LunarLander-v3",
"repo_id": "while0628/LunarLander-v3-u8",
"total_timesteps": 1000000,
"learning_rate": 0.00025,
"num_envs": 4,
"num_steps": 1024,
"anneal_lr": 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": 0.01,
"vf_coef": 0.5,
"max_grad_norm": 0.5,
"target_kl": null,
"seed": 1,
"cuda": true,
"upload": true,
"eval_episodes": 10,
"batch_size": 4096,
"minibatch_size": 1024
}