wmFrank commited on
Commit
13a684b
1 Parent(s): 3ee6979

Upload cfg.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. cfg.json +129 -0
cfg.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "atari_pong",
5
+ "experiment": "01_atari_envs_see_123_env_atari_pong",
6
+ "train_dir": "./train_dir/atari_envs/atari_envs_",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": 123,
10
+ "num_policies": 1,
11
+ "async_rl": false,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 1,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 10000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 1,
20
+ "batch_size": 256,
21
+ "num_batches_per_epoch": 4,
22
+ "num_epochs": 4,
23
+ "rollout": 128,
24
+ "recurrence": 1,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": false,
31
+ "exploration_loss_coeff": 0.01,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "entropy",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 1.0,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-05,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 0.5,
46
+ "learning_rate": 0.00025,
47
+ "lr_schedule": "linear_decay",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "obs_subtract_mean": 0.0,
50
+ "obs_scale": 255.0,
51
+ "normalize_input": false,
52
+ "normalize_input_keys": null,
53
+ "decorrelate_experience_max_seconds": 0,
54
+ "decorrelate_envs_on_one_worker": true,
55
+ "actor_worker_gpus": [],
56
+ "set_workers_cpu_affinity": true,
57
+ "force_envs_single_thread": true,
58
+ "default_niceness": 0,
59
+ "experiment_summaries_interval": 3,
60
+ "stats_avg": 100,
61
+ "summaries_use_frameskip": false,
62
+ "train_for_env_steps": 10000000,
63
+ "train_for_seconds": 10000000000,
64
+ "save_every_sec": 120,
65
+ "keep_checkpoints": 3,
66
+ "load_checkpoint_kind": "latest",
67
+ "save_milestones_sec": -1,
68
+ "save_best_every_sec": 5,
69
+ "save_best_metric": "reward",
70
+ "save_best_after": 100000,
71
+ "benchmark": false,
72
+ "encoder_type": "conv",
73
+ "encoder_subtype": "convnet_atari",
74
+ "encoder_custom": null,
75
+ "encoder_extra_fc_layers": 1,
76
+ "hidden_size": 512,
77
+ "nonlinearity": "relu",
78
+ "policy_initialization": "orthogonal",
79
+ "policy_init_gain": 1.0,
80
+ "actor_critic_share_weights": true,
81
+ "adaptive_stddev": false,
82
+ "initial_stddev": 1.0,
83
+ "use_rnn": false,
84
+ "rnn_type": "gru",
85
+ "rnn_num_layers": 1,
86
+ "env_gpu_actions": false,
87
+ "env_frameskip": 4,
88
+ "env_framestack": 4,
89
+ "pixel_format": "CHW",
90
+ "use_record_episode_statistics": true,
91
+ "with_wandb": true,
92
+ "wandb_user": null,
93
+ "wandb_project": "atari-benchmark",
94
+ "wandb_group": "atari_all",
95
+ "wandb_job_type": "SF",
96
+ "wandb_tags": [
97
+ "run5"
98
+ ],
99
+ "with_pbt": false,
100
+ "pbt_mix_policies_in_one_env": true,
101
+ "pbt_period_env_steps": 5000000,
102
+ "pbt_start_mutation": 20000000,
103
+ "pbt_replace_fraction": 0.3,
104
+ "pbt_mutation_rate": 0.15,
105
+ "pbt_replace_reward_gap": 0.1,
106
+ "pbt_replace_reward_gap_absolute": 1e-06,
107
+ "pbt_optimize_batch_size": false,
108
+ "pbt_optimize_gamma": false,
109
+ "pbt_target_objective": "true_objective",
110
+ "pbt_perturb_min": 1.05,
111
+ "pbt_perturb_max": 1.5,
112
+ "command_line": "--algo=APPO --with_wandb=True --wandb_project=atari-benchmark --wandb_group=atari_all --wandb_tags run5 --seed=123 --env=atari_pong --experiment=01_atari_envs_see_123_env_atari_pong --train_dir=./train_dir/atari_envs/atari_envs_",
113
+ "cli_args": {
114
+ "algo": "APPO",
115
+ "env": "atari_pong",
116
+ "experiment": "01_atari_envs_see_123_env_atari_pong",
117
+ "train_dir": "./train_dir/atari_envs/atari_envs_",
118
+ "seed": 123,
119
+ "with_wandb": true,
120
+ "wandb_project": "atari-benchmark",
121
+ "wandb_group": "atari_all",
122
+ "wandb_tags": [
123
+ "run5"
124
+ ]
125
+ },
126
+ "git_hash": "unknown",
127
+ "git_repo_name": "not a git repository",
128
+ "wandb_unique_id": "01_atari_envs_see_123_env_atari_pong_20220727_174745_048413"
129
+ }