Hugging Face's logo

LLParallax
/
sample_factory_human_monk

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Metrics Community
sample_factory_human_monk
File size: 4,916 Bytes 
673f32c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "help": false,
  "algo": "APPO",
  "env": "nethack_challenge",
  "experiment": "default_experiment",
  "train_dir": "/net/tscratch/people/plgbartekcupial/mrunner_scratch/sample_factory_nethack/03_01-17_00-vigilant_hodgkin/2023-12-28-monk-appo_4m9d_2/train_dir",
  "restart_behavior": "resume",
  "device": "gpu",
  "seed": 2,
  "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": 16,
  "num_envs_per_worker": 32,
  "batch_size": 4096,
  "num_batches_per_epoch": 1,
  "num_epochs": 1,
  "rollout": 32,
  "recurrence": 32,
  "shuffle_minibatches": false,
  "gamma": 0.999,
  "reward_scale": 1.0,
  "reward_clip": 10.0,
  "value_bootstrap": false,
  "normalize_returns": true,
  "exploration_loss_coeff": 0.001,
  "value_loss_coeff": 1.0,
  "kl_loss_coeff": 0.0,
  "exploration_loss": "entropy",
  "gae_lambda": 1.0,
  "ppo_clip_ratio": 0.1,
  "ppo_clip_value": 1.0,
  "with_vtrace": false,
  "vtrace_rho": 1.0,
  "vtrace_c": 1.0,
  "optimizer": "adam",
  "adam_eps": 1e-07,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "max_grad_norm": 4,
  "learning_rate": 0.0001,
  "lr_schedule": "constant",
  "lr_schedule_kl_threshold": 0.008,
  "lr_adaptive_min": 1e-06,
  "lr_adaptive_max": 0.01,
  "obs_subtract_mean": 0.0,
  "obs_scale": 1.0,
  "normalize_input": false,
  "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": 50,
  "flush_summaries_interval": 30,
  "stats_avg": 100,
  "summaries_use_frameskip": true,
  "heartbeat_interval": 20,
  "heartbeat_reporting_interval": 180,
  "train_for_env_steps": 2000000000,
  "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": "lstm",
  "rnn_num_layers": 1,
  "decoder_mlp_layers": [],
  "nonlinearity": "relu",
  "policy_initialization": "orthogonal",
  "policy_init_gain": 1.0,
  "actor_critic_share_weights": true,
  "adaptive_stddev": false,
  "continuous_tanh_scale": 0.0,
  "initial_stddev": 1.0,
  "use_env_info_cache": false,
  "env_gpu_actions": false,
  "env_gpu_observations": true,
  "env_frameskip": 1,
  "env_framestack": 1,
  "pixel_format": "CHW",
  "use_record_episode_statistics": false,
  "episode_counter": false,
  "with_wandb": true,
  "wandb_user": "bartekcupial",
  "wandb_project": "sample_factory_nethack",
  "wandb_group": "gmum",
  "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,
  "character": "mon-hum-neu-mal",
  "max_episode_steps": 100000,
  "penalty_step": 0.0,
  "penalty_time": 0.0,
  "fn_penalty_step": "constant",
  "savedir": null,
  "save_ttyrec_every": 0,
  "add_image_observation": true,
  "crop_dim": 18,
  "pixel_size": 6,
  "use_prev_action": true,
  "use_tty_only": true,
  "model": "ChaoticDwarvenGPT5",
  "add_stats_to_info": true,
  "command_line": "--env=nethack_challenge --train_for_env_steps=2000000000 --character=mon-hum-neu-mal --num_workers=16 --num_envs_per_worker=32 --worker_num_splits=2 --rollout=32 --batch_size=4096 --async_rl=True --serial_mode=False --wandb_user=bartekcupial --wandb_project=sample_factory_nethack --wandb_group=gmum --with_wandb=True --use_prev_action=True --model=ChaoticDwarvenGPT5 --rnn_size=512 --seed=2",
  "cli_args": {
    "env": "nethack_challenge",
    "seed": 2,
    "async_rl": true,
    "serial_mode": false,
    "worker_num_splits": 2,
    "num_workers": 16,
    "num_envs_per_worker": 32,
    "batch_size": 4096,
    "rollout": 32,
    "train_for_env_steps": 2000000000,
    "rnn_size": 512,
    "with_wandb": true,
    "wandb_user": "bartekcupial",
    "wandb_project": "sample_factory_nethack",
    "wandb_group": "gmum",
    "character": "mon-hum-neu-mal",
    "use_prev_action": true,
    "model": "ChaoticDwarvenGPT5"
  },
  "git_hash": "unknown",
  "git_repo_name": "not a git repository",
  "wandb_unique_id": "default_experiment_20240103_191716_696528"
}