Upload folder using huggingface_hub
Browse files- .summary/0/events.out.tfevents.1690158571.11c477af595d +3 -0
- .summary/0/events.out.tfevents.1690158643.11c477af595d +3 -0
- .summary/0/events.out.tfevents.1690158742.11c477af595d +3 -0
- .summary/0/events.out.tfevents.1690158839.11c477af595d +3 -0
- README.md +6 -6
- checkpoint_p0/best_000000113_462848_reward_-2.703.pth +3 -0
- checkpoint_p0/checkpoint_000001447_5926912.pth +3 -0
- checkpoint_p0/checkpoint_000001466_6004736.pth +3 -0
- config.json +8 -8
- replay.mp4 +2 -2
- sf_log.txt +0 -0
.summary/0/events.out.tfevents.1690158571.11c477af595d
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94bdd879a0109762a6cdce9f2e0535de8e3a847021c27826bcc9087681342db4
|
3 |
+
size 40
|
.summary/0/events.out.tfevents.1690158643.11c477af595d
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5aa61c110fc96828e2193a122bc9b3f85b850078d4a7f2ee4e245f74611004
|
3 |
+
size 7843
|
.summary/0/events.out.tfevents.1690158742.11c477af595d
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e658e58317575cacbd3230ed870ab315919aee4c2a34fcd6fc2c10836b52ea48
|
3 |
+
size 2892
|
.summary/0/events.out.tfevents.1690158839.11c477af595d
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6861b6836287aae2917b58af3c158bd6df11fe2f2a33b04f583f20bc94e4811
|
3 |
+
size 2683560
|
README.md
CHANGED
@@ -11,16 +11,16 @@ model-index:
|
|
11 |
type: reinforcement-learning
|
12 |
name: reinforcement-learning
|
13 |
dataset:
|
14 |
-
name:
|
15 |
-
type:
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
-
value:
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
22 |
|
23 |
-
A(n) **APPO** model trained on the **
|
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/
|
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r Corianas/rl_course_vizdoom
|
|
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=
|
42 |
```
|
43 |
|
44 |
|
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
|
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=
|
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.
|
|
|
11 |
type: reinforcement-learning
|
12 |
name: reinforcement-learning
|
13 |
dataset:
|
14 |
+
name: doom_deathmatch_bots
|
15 |
+
type: doom_deathmatch_bots
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
+
value: 1.30 +/- 1.19
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
22 |
|
23 |
+
A(n) **APPO** model trained on the **doom_deathmatch_bots** 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/
|
|
|
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=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
|
42 |
```
|
43 |
|
44 |
|
|
|
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=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --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.
|
checkpoint_p0/best_000000113_462848_reward_-2.703.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e88113be823414a8311235c15b73430b2f41d16243287a51240c23adf5f7e5c
|
3 |
+
size 37738579
|
checkpoint_p0/checkpoint_000001447_5926912.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06b5c86642735e6433da16ab7fb21e48dac02e50a08dac04883ed44e784fc1a7
|
3 |
+
size 37739171
|
checkpoint_p0/checkpoint_000001466_6004736.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beb4516467a6224e401ab39da7d7d9a71c41a31e5fef902181c861b1f293990c
|
3 |
+
size 37739171
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"help": false,
|
3 |
"algo": "APPO",
|
4 |
-
"env": "
|
5 |
"experiment": "default_experiment",
|
6 |
"train_dir": "/content/train_dir",
|
7 |
"restart_behavior": "resume",
|
@@ -16,7 +16,7 @@
|
|
16 |
"policy_workers_per_policy": 1,
|
17 |
"max_policy_lag": 1000,
|
18 |
"num_workers": 8,
|
19 |
-
"num_envs_per_worker":
|
20 |
"batch_size": 1024,
|
21 |
"num_batches_per_epoch": 1,
|
22 |
"num_epochs": 1,
|
@@ -65,7 +65,7 @@
|
|
65 |
"summaries_use_frameskip": true,
|
66 |
"heartbeat_interval": 20,
|
67 |
"heartbeat_reporting_interval": 600,
|
68 |
-
"train_for_env_steps":
|
69 |
"train_for_seconds": 10000000000,
|
70 |
"save_every_sec": 120,
|
71 |
"keep_checkpoints": 2,
|
@@ -99,7 +99,7 @@
|
|
99 |
"env_gpu_actions": false,
|
100 |
"env_gpu_observations": true,
|
101 |
"env_frameskip": 4,
|
102 |
-
"env_framestack":
|
103 |
"pixel_format": "CHW",
|
104 |
"use_record_episode_statistics": false,
|
105 |
"with_wandb": false,
|
@@ -130,12 +130,12 @@
|
|
130 |
"wide_aspect_ratio": false,
|
131 |
"eval_env_frameskip": 1,
|
132 |
"fps": 35,
|
133 |
-
"command_line": "--env=
|
134 |
"cli_args": {
|
135 |
-
"env": "
|
136 |
"num_workers": 8,
|
137 |
-
"num_envs_per_worker":
|
138 |
-
"train_for_env_steps":
|
139 |
},
|
140 |
"git_hash": "unknown",
|
141 |
"git_repo_name": "not a git repository"
|
|
|
1 |
{
|
2 |
"help": false,
|
3 |
"algo": "APPO",
|
4 |
+
"env": "doom_deathmatch_bots",
|
5 |
"experiment": "default_experiment",
|
6 |
"train_dir": "/content/train_dir",
|
7 |
"restart_behavior": "resume",
|
|
|
16 |
"policy_workers_per_policy": 1,
|
17 |
"max_policy_lag": 1000,
|
18 |
"num_workers": 8,
|
19 |
+
"num_envs_per_worker": 8,
|
20 |
"batch_size": 1024,
|
21 |
"num_batches_per_epoch": 1,
|
22 |
"num_epochs": 1,
|
|
|
65 |
"summaries_use_frameskip": true,
|
66 |
"heartbeat_interval": 20,
|
67 |
"heartbeat_reporting_interval": 600,
|
68 |
+
"train_for_env_steps": 6000000,
|
69 |
"train_for_seconds": 10000000000,
|
70 |
"save_every_sec": 120,
|
71 |
"keep_checkpoints": 2,
|
|
|
99 |
"env_gpu_actions": false,
|
100 |
"env_gpu_observations": true,
|
101 |
"env_frameskip": 4,
|
102 |
+
"env_framestack": 3,
|
103 |
"pixel_format": "CHW",
|
104 |
"use_record_episode_statistics": false,
|
105 |
"with_wandb": false,
|
|
|
130 |
"wide_aspect_ratio": false,
|
131 |
"eval_env_frameskip": 1,
|
132 |
"fps": 35,
|
133 |
+
"command_line": "--env=doom_deathmatch_bots --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
|
134 |
"cli_args": {
|
135 |
+
"env": "doom_deathmatch_bots",
|
136 |
"num_workers": 8,
|
137 |
+
"num_envs_per_worker": 4,
|
138 |
+
"train_for_env_steps": 4000000
|
139 |
},
|
140 |
"git_hash": "unknown",
|
141 |
"git_repo_name": "not a git repository"
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:458e608759cca0c76d1dcf6ada7e3cadcc9d4f67952c47026958bd8d426c3b9d
|
3 |
+
size 144308102
|
sf_log.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|