Hugging Face's logo

mojemai
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
rl_course_vizdoom_health_gathering_supreme
File size: 3,936 Bytes 
eca00cf
 
 
 
 
32bb4d3
eca00cf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32bb4d3
eca00cf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32bb4d3
eca00cf
 
 
 
32bb4d3
eca00cf
32bb4d3
 
 
eca00cf
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
{
  "help": false,
  "algo": "APPO",
  "env": "doom_health_gathering_supreme",
  "experiment": "default_experiment",
  "train_dir": "/home/ubuntu/hf-deep-rl-course/unit8/train_dir",
  "restart_behavior": "resume",
  "device": "gpu",
  "seed": null,
  "num_policies": 1,
  "async_rl": true,
  "serial_mode": false,
  "batched_sampling": false,
  "num_batches_to_accumulate": 2,
  "worker_num_splits": 2,
  "policy_workers_per_policy": 1,
  "max_policy_lag": 1000,
  "num_workers": 8,
  "num_envs_per_worker": 4,
  "batch_size": 1024,
  "num_batches_per_epoch": 1,
  "num_epochs": 1,
  "rollout": 32,
  "recurrence": 32,
  "shuffle_minibatches": false,
  "gamma": 0.99,
  "reward_scale": 1.0,
  "reward_clip": 1000.0,
  "value_bootstrap": false,
  "normalize_returns": true,
  "exploration_loss_coeff": 0.001,
  "value_loss_coeff": 0.5,
  "kl_loss_coeff": 0.0,
  "exploration_loss": "symmetric_kl",
  "gae_lambda": 0.95,
  "ppo_clip_ratio": 0.1,
  "ppo_clip_value": 0.2,
  "with_vtrace": false,
  "vtrace_rho": 1.0,
  "vtrace_c": 1.0,
  "optimizer": "adam",
  "adam_eps": 1e-06,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "max_grad_norm": 4.0,
  "learning_rate": 0.0001,
  "lr_schedule": "constant",
  "lr_schedule_kl_threshold": 0.008,
  "obs_subtract_mean": 0.0,
  "obs_scale": 255.0,
  "normalize_input": true,
  "normalize_input_keys": null,
  "decorrelate_experience_max_seconds": 0,
  "decorrelate_envs_on_one_worker": true,
  "actor_worker_gpus": [],
  "set_workers_cpu_affinity": true,
  "force_envs_single_thread": false,
  "default_niceness": 0,
  "log_to_file": true,
  "experiment_summaries_interval": 10,
  "flush_summaries_interval": 30,
  "stats_avg": 100,
  "summaries_use_frameskip": true,
  "heartbeat_interval": 20,
  "heartbeat_reporting_interval": 600,
  "train_for_env_steps": 10000000,
  "train_for_seconds": 10000000000,
  "save_every_sec": 120,
  "keep_checkpoints": 2,
  "load_checkpoint_kind": "latest",
  "save_milestones_sec": -1,
  "save_best_every_sec": 5,
  "save_best_metric": "reward",
  "save_best_after": 100000,
  "benchmark": false,
  "encoder_mlp_layers": [
    512,
    512
  ],
  "encoder_conv_architecture": "convnet_simple",
  "encoder_conv_mlp_layers": [
    512
  ],
  "use_rnn": true,
  "rnn_size": 512,
  "rnn_type": "gru",
  "rnn_num_layers": 1,
  "decoder_mlp_layers": [],
  "nonlinearity": "elu",
  "policy_initialization": "orthogonal",
  "policy_init_gain": 1.0,
  "actor_critic_share_weights": true,
  "adaptive_stddev": true,
  "continuous_tanh_scale": 0.0,
  "initial_stddev": 1.0,
  "use_env_info_cache": false,
  "env_gpu_actions": false,
  "env_gpu_observations": true,
  "env_frameskip": 4,
  "env_framestack": 1,
  "pixel_format": "CHW",
  "use_record_episode_statistics": false,
  "with_wandb": false,
  "wandb_user": null,
  "wandb_project": "sample_factory",
  "wandb_group": null,
  "wandb_job_type": "SF",
  "wandb_tags": [],
  "with_pbt": false,
  "pbt_mix_policies_in_one_env": true,
  "pbt_period_env_steps": 5000000,
  "pbt_start_mutation": 20000000,
  "pbt_replace_fraction": 0.3,
  "pbt_mutation_rate": 0.15,
  "pbt_replace_reward_gap": 0.1,
  "pbt_replace_reward_gap_absolute": 1e-06,
  "pbt_optimize_gamma": false,
  "pbt_target_objective": "true_objective",
  "pbt_perturb_min": 1.1,
  "pbt_perturb_max": 1.5,
  "num_agents": -1,
  "num_humans": 0,
  "num_bots": -1,
  "start_bot_difficulty": null,
  "timelimit": null,
  "res_w": 128,
  "res_h": 72,
  "wide_aspect_ratio": false,
  "eval_env_frameskip": 1,
  "fps": 35,
  "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=10000000",
  "cli_args": {
    "env": "doom_health_gathering_supreme",
    "num_workers": 8,
    "num_envs_per_worker": 4,
    "train_for_env_steps": 10000000
  },
  "git_hash": "2c9ebb46ab6522686b0ac8ed204567b32ae6dcfc",
  "git_repo_name": "https://github.com/phalanx8/hf-deep-rl-course",
  "train_script": "unit8-part2"
}