edbeeching HF staff commited on
Commit
949a04b
1 Parent(s): 923e97f

Upload folder using huggingface_hub

Browse files
.summary/0/events.out.tfevents.1688632896.PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971a4fd085a41df29bf7839f1e4e059767581778637ab9918949fb79f86a23c1
3
+ size 40
.summary/0/events.out.tfevents.1688632907.PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b408e498d4059b65f67442ab08e1ccb0e85519b2d8b6c60f1e423c6a13401059
3
+ size 40
.summary/0/events.out.tfevents.1688632944.PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedb008478aba58fc6859fe3fd2e085d8d5f8827f98a2d4ff7e64b7049dd2448
3
+ size 7939852
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: atari_surround
15
+ type: atari_surround
16
+ metrics:
17
+ - type: mean_reward
18
+ value: nan +/- nan
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **atari_surround** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r edbeeching/atari_2B_atari_surround_1111
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=atari_surround --train_dir=./train_dir --experiment=atari_2B_atari_surround_1111
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=atari_surround --train_dir=./train_dir --experiment=atari_2B_atari_surround_1111 --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000746384_1528594432_reward_9.990.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e6ccb7bd8d9339eaf266ebcfb1dffc83d5e1f36d04c2d0f687341874f1a750
3
+ size 20715699
checkpoint_p0/checkpoint_000976608_2000093184.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acf7298e4c0d2105f1e4461f30b985b353e99b4eed63a9d6ed50f8e81403ed0
3
+ size 20716035
checkpoint_p0/checkpoint_000976624_2000125952.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41213da5244848d247a8369461333d7e14ae2f735488ce372d50b5a3b72da9c3
3
+ size 20716035
checkpoint_p0/milestones/checkpoint_000063920_130908160.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705265243b22c5e42e0ded606043e121f3c26130095475edaa536c67f50d8c8f
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000129488_265191424.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d2c7a91b42cc8692e40eb560cd18e7ef6b6092fb52fc4a2e396ca5075a8797
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000195008_399376384.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b85945496b97f4a00c1e71fe0224b05e448ddc94ee3f639f97e157462908ad
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000260352_533200896.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9234c54d3d3ed2f99d5f7e7747ce80d3d0d39d776fdbe1f4caacd5837a6d4801
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000325696_667025408.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ac256d05adf235ab6b9b24edaf03eb625a6813b26a68e1b967a26051308264
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000391024_800817152.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d0498336eee4ea7477872882aef20c1a615d53a55402e268263b7b71a70039
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000456448_934805504.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:007102c48f99c08d3b8d3edbf77647b6132aca1889373050df0e6ebc1bf29881
3
+ size 20717003
checkpoint_p0/milestones/checkpoint_000521472_1067974656.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435a26ab9f7bfce2fef493de3eccaef02a49b80032c6d4c1ac6b2f90a0be15cf
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000586816_1201799168.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df573306b52b6a185f7470be5a13f6735790506b3b575386aafcbfec50be850f
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000652288_1335885824.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18637187b32569cd5d39aecd722c79ad2130bb174aa31c6bf8ef934b9393dc6c
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000717600_1469644800.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d1e215171fa08f2dfc3b2729f0fd963ddd6d8c0564ccb08f8ad8791425522b
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000782080_1601699840.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c113f7063797c8473b972f4734a8970a38e97e0adc814d19915a7abb49d195c
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000846240_1733099520.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04a087eb095bf74653b300f1c8e4cb425113dac814cb81ddea55db9d351383c
3
+ size 20717059
checkpoint_p0/milestones/checkpoint_000911616_1866989568.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432889e5aa5fff8878ee5abd82dda29a562fabe27c0d9849498860f2339c3c10
3
+ size 20717059
config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "atari_surround",
5
+ "experiment": "20221014_2B__atari_surround_1111",
6
+ "train_dir": "train_dir/atari_2b",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": 1111,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": true,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 1,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 4,
19
+ "num_envs_per_worker": 1,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 8,
22
+ "num_epochs": 2,
23
+ "rollout": 64,
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": true,
31
+ "exploration_loss_coeff": 0.0004677351413,
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": 0.0,
46
+ "learning_rate": 0.0003033891184,
47
+ "lr_schedule": "linear_decay",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": [
55
+ "obs"
56
+ ],
57
+ "decorrelate_experience_max_seconds": 1,
58
+ "decorrelate_envs_on_one_worker": true,
59
+ "actor_worker_gpus": [],
60
+ "set_workers_cpu_affinity": true,
61
+ "force_envs_single_thread": false,
62
+ "default_niceness": 0,
63
+ "log_to_file": true,
64
+ "experiment_summaries_interval": 3,
65
+ "flush_summaries_interval": 30,
66
+ "stats_avg": 100,
67
+ "summaries_use_frameskip": true,
68
+ "heartbeat_interval": 20,
69
+ "heartbeat_reporting_interval": 180,
70
+ "train_for_env_steps": 2000000000,
71
+ "train_for_seconds": 3600000,
72
+ "save_every_sec": 120,
73
+ "keep_checkpoints": 2,
74
+ "load_checkpoint_kind": "latest",
75
+ "save_milestones_sec": 1200,
76
+ "save_best_every_sec": 5,
77
+ "save_best_metric": "reward",
78
+ "save_best_after": 100000,
79
+ "benchmark": false,
80
+ "encoder_mlp_layers": [
81
+ 512,
82
+ 512
83
+ ],
84
+ "encoder_conv_architecture": "convnet_atari",
85
+ "encoder_conv_mlp_layers": [
86
+ 512
87
+ ],
88
+ "use_rnn": false,
89
+ "rnn_size": 512,
90
+ "rnn_type": "gru",
91
+ "rnn_num_layers": 1,
92
+ "decoder_mlp_layers": [],
93
+ "nonlinearity": "relu",
94
+ "policy_initialization": "orthogonal",
95
+ "policy_init_gain": 1.0,
96
+ "actor_critic_share_weights": true,
97
+ "adaptive_stddev": false,
98
+ "continuous_tanh_scale": 0.0,
99
+ "initial_stddev": 1.0,
100
+ "use_env_info_cache": false,
101
+ "env_gpu_actions": false,
102
+ "env_gpu_observations": true,
103
+ "env_frameskip": 4,
104
+ "env_framestack": 4,
105
+ "pixel_format": "CHW",
106
+ "use_record_episode_statistics": true,
107
+ "with_wandb": false,
108
+ "wandb_user": null,
109
+ "wandb_project": "sample_factory",
110
+ "wandb_group": null,
111
+ "wandb_job_type": "SF",
112
+ "wandb_tags": [],
113
+ "with_pbt": false,
114
+ "pbt_mix_policies_in_one_env": true,
115
+ "pbt_period_env_steps": 5000000,
116
+ "pbt_start_mutation": 20000000,
117
+ "pbt_replace_fraction": 0.3,
118
+ "pbt_mutation_rate": 0.15,
119
+ "pbt_replace_reward_gap": 0.1,
120
+ "pbt_replace_reward_gap_absolute": 1e-06,
121
+ "pbt_optimize_gamma": false,
122
+ "pbt_target_objective": "true_objective",
123
+ "pbt_perturb_min": 1.1,
124
+ "pbt_perturb_max": 1.5,
125
+ "env_agents": 512,
126
+ "command_line": "--seed=1111 --experiment=20221014_2B__atari_surround_1111 --env=atari_surround --train_for_seconds=3600000 --algo=APPO --gamma=0.99 --num_workers=4 --num_envs_per_worker=1 --worker_num_splits=1 --env_agents=512 --benchmark=False --max_grad_norm=0.0 --decorrelate_experience_max_seconds=1 --encoder_conv_architecture=convnet_atari --encoder_conv_mlp_layers 512 --nonlinearity=relu --num_policies=1 --normalize_input=True --normalize_input_keys obs --normalize_returns=True --async_rl=True --batched_sampling=True --train_for_env_steps=2000000000 --save_milestones_sec=1200 --train_dir train_dir/atari_2b --rollout 64 --exploration_loss_coeff 0.0004677351413 --num_epochs 2 --batch_size 1024 --num_batches_per_epoch 8 --learning_rate 0.0003033891184",
127
+ "cli_args": {
128
+ "algo": "APPO",
129
+ "env": "atari_surround",
130
+ "experiment": "20221014_2B__atari_surround_1111",
131
+ "train_dir": "train_dir/atari_2b",
132
+ "seed": 1111,
133
+ "num_policies": 1,
134
+ "async_rl": true,
135
+ "batched_sampling": true,
136
+ "worker_num_splits": 1,
137
+ "num_workers": 4,
138
+ "num_envs_per_worker": 1,
139
+ "batch_size": 1024,
140
+ "num_batches_per_epoch": 8,
141
+ "num_epochs": 2,
142
+ "rollout": 64,
143
+ "gamma": 0.99,
144
+ "normalize_returns": true,
145
+ "exploration_loss_coeff": 0.0004677351413,
146
+ "max_grad_norm": 0.0,
147
+ "learning_rate": 0.0003033891184,
148
+ "normalize_input": true,
149
+ "normalize_input_keys": [
150
+ "obs"
151
+ ],
152
+ "decorrelate_experience_max_seconds": 1,
153
+ "train_for_env_steps": 2000000000,
154
+ "train_for_seconds": 3600000,
155
+ "save_milestones_sec": 1200,
156
+ "benchmark": false,
157
+ "encoder_conv_architecture": "convnet_atari",
158
+ "encoder_conv_mlp_layers": [
159
+ 512
160
+ ],
161
+ "nonlinearity": "relu",
162
+ "env_agents": 512
163
+ },
164
+ "git_hash": "7e1e69550f4de4cdc003d8db5bb39e186803aee9",
165
+ "git_repo_name": "git@github.com:alex-petrenko/sample-factory.git"
166
+ }
git.diff ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ diff --git a/sf_examples/mujoco/experiments/mujoco_all_envs.py b/sf_examples/mujoco/experiments/mujoco_all_envs.py
2
+ index 452c451a..a862b4c0 100644
3
+ --- a/sf_examples/mujoco/experiments/mujoco_all_envs.py
4
+ +++ b/sf_examples/mujoco/experiments/mujoco_all_envs.py
5
+ @@ -2,19 +2,13 @@ from sample_factory.launcher.run_description import Experiment, ParamGrid, RunDe
6
+
7
+ _params = ParamGrid(
8
+ [
9
+ - ("seed", [0, 1111, 2222, 3333, 4444, 5555, 6666, 7777, 8888, 9999]),
10
+ + ("seed", [1111]),
11
+ (
12
+ "env",
13
+ [
14
+ - "mujoco_ant",
15
+ - "mujoco_halfcheetah",
16
+ - "mujoco_hopper",
17
+ "mujoco_humanoid",
18
+ - "mujoco_doublependulum",
19
+ - "mujoco_pendulum",
20
+ + "mujoco_standup",
21
+ "mujoco_reacher",
22
+ - "mujoco_swimmer",
23
+ - "mujoco_walker",
24
+ ],
25
+ ),
26
+ ]
sf_log.txt ADDED
The diff for this file is too large to render. See raw diff