| { | |
| "algo": "ppo", | |
| "game": "phoenix", | |
| "seed": 0, | |
| "tag": "", | |
| "total_steps": 2000000, | |
| "num_envs": 16, | |
| "sticky": 0.25, | |
| "noop_max": 30, | |
| "max_frames": 108000, | |
| "clip_reward": true, | |
| "arch": "impala", | |
| "hidden": 256, | |
| "lr": 0.00025, | |
| "lr_anneal": true, | |
| "adam_eps": 1e-05, | |
| "max_grad_norm": 0.5, | |
| "gamma": 0.99, | |
| "gae_lambda": 0.95, | |
| "n_steps": 128, | |
| "ent_coef": 0.01, | |
| "vf_coef": 0.5, | |
| "norm_adv": true, | |
| "clip_eps": 0.1, | |
| "ppo_epochs": 4, | |
| "minibatches": 4, | |
| "clip_vloss": false, | |
| "target_kl": null, | |
| "baseline": "batch", | |
| "max_episode_steps": 4000, | |
| "chunk": 512, | |
| "eval_every": 300000, | |
| "eval_episodes": 8, | |
| "ckpt_every": 500000, | |
| "print_every_s": 20.0, | |
| "device": "auto" | |
| } |