MattStammers
commited on
Commit
•
42df274
1
Parent(s):
90cf1c3
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- .summary/0/events.out.tfevents.1695669510.rhmmedcatt-proliant-ml350-gen10 +3 -0
- .summary/1/events.out.tfevents.1695669510.rhmmedcatt-proliant-ml350-gen10 +3 -0
- README.md +56 -0
- checkpoint_p0/best_000006176_1581056_reward_9.890.pth +3 -0
- checkpoint_p0/checkpoint_000038064_9744384.pth +3 -0
- checkpoint_p0/checkpoint_000039088_10006528.pth +3 -0
- checkpoint_p1/best_000035824_9170944_reward_9.990.pth +3 -0
- checkpoint_p1/checkpoint_000038064_9744384.pth +3 -0
- checkpoint_p1/checkpoint_000039088_10006528.pth +3 -0
- config.json +144 -0
- git.diff +3 -0
- replay.mp4 +3 -0
- sf_log.txt +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
git.diff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
.summary/0/events.out.tfevents.1695669510.rhmmedcatt-proliant-ml350-gen10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0134652f1d7f438f77d91685f28e3498a6690197aa19903e279930cd89d225c1
|
3 |
+
size 1999971
|
.summary/1/events.out.tfevents.1695669510.rhmmedcatt-proliant-ml350-gen10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7d6756f316da750700afe65a070a8f24e47172d4f7344846639233a7bd52fed
|
3 |
+
size 1298191
|
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_bowling
|
15 |
+
type: atari_bowling
|
16 |
+
metrics:
|
17 |
+
- type: mean_reward
|
18 |
+
value: 97.10 +/- 7.74
|
19 |
+
name: mean_reward
|
20 |
+
verified: false
|
21 |
+
---
|
22 |
+
|
23 |
+
A(n) **APPO** model trained on the **atari_bowling** 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 MattStammers/appo-atari_bowling
|
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 sf_examples.atari.enjoy_atari --algo=APPO --env=atari_bowling --train_dir=./train_dir --experiment=appo-atari_bowling
|
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 sf_examples.atari.train_atari --algo=APPO --env=atari_bowling --train_dir=./train_dir --experiment=appo-atari_bowling --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_000006176_1581056_reward_9.890.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09cf0583b074f66c9ac4e4b08c9bab049d79a0a9b60356ec7862feb9c0fc9bb0
|
3 |
+
size 20721843
|
checkpoint_p0/checkpoint_000038064_9744384.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac02171fe5478a61d7a5e5a004bdfaad1447f224646a6099a26b61b2433c2075
|
3 |
+
size 20722179
|
checkpoint_p0/checkpoint_000039088_10006528.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c9a3c87aaf961f5e4b1833a4f30a7b48b8337de907c4f9810a732e1f5d74a49
|
3 |
+
size 20722179
|
checkpoint_p1/best_000035824_9170944_reward_9.990.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08da4b68f591774a5a7aa1619cfe9c4d72eb4bc8c7b53c061168cd3ea4196bda
|
3 |
+
size 20721843
|
checkpoint_p1/checkpoint_000038064_9744384.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3c600ba737b3894f3b0fb3da7f632969e5e4f78bfae1de0708696b2308e2adc
|
3 |
+
size 20722179
|
checkpoint_p1/checkpoint_000039088_10006528.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e205b9607404bcab1c8861bad0bb7a773615ce1dad350f682ea0e05f7319cf81
|
3 |
+
size 20722179
|
config.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"help": false,
|
3 |
+
"algo": "APPO",
|
4 |
+
"env": "atari_bowling",
|
5 |
+
"experiment": "atari_bowling",
|
6 |
+
"train_dir": "./train_atari",
|
7 |
+
"restart_behavior": "resume",
|
8 |
+
"device": "gpu",
|
9 |
+
"seed": null,
|
10 |
+
"num_policies": 2,
|
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": 1000,
|
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": true,
|
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 |
+
"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": null,
|
55 |
+
"decorrelate_experience_max_seconds": 0,
|
56 |
+
"decorrelate_envs_on_one_worker": true,
|
57 |
+
"actor_worker_gpus": [],
|
58 |
+
"set_workers_cpu_affinity": true,
|
59 |
+
"force_envs_single_thread": false,
|
60 |
+
"default_niceness": 0,
|
61 |
+
"log_to_file": true,
|
62 |
+
"experiment_summaries_interval": 3,
|
63 |
+
"flush_summaries_interval": 30,
|
64 |
+
"stats_avg": 100,
|
65 |
+
"summaries_use_frameskip": true,
|
66 |
+
"heartbeat_interval": 20,
|
67 |
+
"heartbeat_reporting_interval": 180,
|
68 |
+
"train_for_env_steps": 10000000,
|
69 |
+
"train_for_seconds": 10000000000,
|
70 |
+
"save_every_sec": 120,
|
71 |
+
"keep_checkpoints": 2,
|
72 |
+
"load_checkpoint_kind": "latest",
|
73 |
+
"save_milestones_sec": -1,
|
74 |
+
"save_best_every_sec": 5,
|
75 |
+
"save_best_metric": "reward",
|
76 |
+
"save_best_after": 100000,
|
77 |
+
"benchmark": false,
|
78 |
+
"encoder_mlp_layers": [
|
79 |
+
512,
|
80 |
+
512
|
81 |
+
],
|
82 |
+
"encoder_conv_architecture": "convnet_atari",
|
83 |
+
"encoder_conv_mlp_layers": [
|
84 |
+
512
|
85 |
+
],
|
86 |
+
"use_rnn": false,
|
87 |
+
"rnn_size": 512,
|
88 |
+
"rnn_type": "gru",
|
89 |
+
"rnn_num_layers": 1,
|
90 |
+
"decoder_mlp_layers": [],
|
91 |
+
"nonlinearity": "relu",
|
92 |
+
"policy_initialization": "orthogonal",
|
93 |
+
"policy_init_gain": 1.0,
|
94 |
+
"actor_critic_share_weights": true,
|
95 |
+
"adaptive_stddev": false,
|
96 |
+
"continuous_tanh_scale": 0.0,
|
97 |
+
"initial_stddev": 1.0,
|
98 |
+
"use_env_info_cache": false,
|
99 |
+
"env_gpu_actions": false,
|
100 |
+
"env_gpu_observations": true,
|
101 |
+
"env_frameskip": 4,
|
102 |
+
"env_framestack": 4,
|
103 |
+
"pixel_format": "CHW",
|
104 |
+
"use_record_episode_statistics": true,
|
105 |
+
"with_wandb": true,
|
106 |
+
"wandb_user": "matt-stammers",
|
107 |
+
"wandb_project": "atari",
|
108 |
+
"wandb_group": "atari_bowling",
|
109 |
+
"wandb_job_type": "SF",
|
110 |
+
"wandb_tags": [
|
111 |
+
"atari"
|
112 |
+
],
|
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 |
+
"command_line": "--algo=APPO --env=atari_bowling --experiment=atari_bowling --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_bowling --wandb_job_type=SF --wandb_tags=atari",
|
126 |
+
"cli_args": {
|
127 |
+
"algo": "APPO",
|
128 |
+
"env": "atari_bowling",
|
129 |
+
"experiment": "atari_bowling",
|
130 |
+
"train_dir": "./train_atari",
|
131 |
+
"num_policies": 2,
|
132 |
+
"with_wandb": true,
|
133 |
+
"wandb_user": "matt-stammers",
|
134 |
+
"wandb_project": "atari",
|
135 |
+
"wandb_group": "atari_bowling",
|
136 |
+
"wandb_job_type": "SF",
|
137 |
+
"wandb_tags": [
|
138 |
+
"atari"
|
139 |
+
]
|
140 |
+
},
|
141 |
+
"git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
|
142 |
+
"git_repo_name": "not a git repository",
|
143 |
+
"wandb_unique_id": "atari_bowling_20230925_201827_962652"
|
144 |
+
}
|
git.diff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f3fe545f35e5db1e419bf1e198c0bc5ef89459d55f59e2d06d3c108907e732
|
3 |
+
size 14403396
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01f494cdb7c66763054d356ab1a905e6a99bbdd4de518dd474dd21ec6def7443
|
3 |
+
size 1386063
|
sf_log.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|