Commit
·
0acb9e4
1
Parent(s):
8e79d2a
Upload folder using huggingface_hub
Browse files- .summary/0/events.out.tfevents.1697015803.rhmmedcatt-proliant-ml350-gen10 +3 -0
- .summary/1/events.out.tfevents.1697015803.rhmmedcatt-proliant-ml350-gen10 +3 -0
- README.md +117 -4
- checkpoint_p0/best_000089472_91619328_reward_34.000.pth +3 -0
- checkpoint_p0/checkpoint_000097216_99549184.pth +3 -0
- checkpoint_p0/checkpoint_000097664_100007936.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000007104_7274496.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000014304_14647296.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000021504_22020096.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000028736_29425664.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000035936_36798464.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000043168_44204032.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000050368_51576832.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000057568_58949632.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000064768_66322432.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000071968_73695232.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000079200_81100800.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000086432_88506368.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000093632_95879168.pth +3 -0
- checkpoint_p1/best_000097280_99614720_reward_34.000.pth +3 -0
- checkpoint_p1/checkpoint_000097792_100139008.pth +3 -0
- checkpoint_p1/checkpoint_000098272_100630528.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000007136_7307264.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000014400_14745600.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000021664_22183936.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000028896_29589504.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000036160_37027840.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000043392_44433408.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000050656_51871744.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000057920_59310080.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000065152_66715648.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000072416_74153984.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000079680_81592320.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000086912_88997888.pth +3 -0
- checkpoint_p1/milestones/checkpoint_000094176_96436224.pth +3 -0
- config.json +40 -22
- git.diff +2 -2
- replay.mp4 +2 -2
- sf_log.txt +0 -0
.summary/0/events.out.tfevents.1697015803.rhmmedcatt-proliant-ml350-gen10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47861e76ad1f2ee182a9e308d8af3fd4f058681399872a01643f8373b6e4a67a
|
| 3 |
+
size 8867618
|
.summary/1/events.out.tfevents.1697015803.rhmmedcatt-proliant-ml350-gen10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84a7847f372bd1502d899a9906a99a4397f77b3727c5c0be7a745a23135a559e
|
| 3 |
+
size 5109253
|
README.md
CHANGED
|
@@ -15,7 +15,7 @@ model-index:
|
|
| 15 |
type: atari_freeway
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
-
value:
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
@@ -30,15 +30,128 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
|
|
| 30 |
|
| 31 |
After installing Sample-Factory, download the model with:
|
| 32 |
```
|
| 33 |
-
python -m sample_factory.huggingface.load_from_hub -r MattStammers/
|
| 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_freeway --train_dir=./train_dir --experiment=
|
| 42 |
```
|
| 43 |
|
| 44 |
|
|
@@ -49,7 +162,7 @@ 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 sf_examples.atari.train_atari --algo=APPO --env=atari_freeway --train_dir=./train_dir --experiment=
|
| 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.
|
|
|
|
| 15 |
type: atari_freeway
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
+
value: 34.00 +/- 0.00
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
|
|
| 30 |
|
| 31 |
After installing Sample-Factory, download the model with:
|
| 32 |
```
|
| 33 |
+
python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_freeway
|
| 34 |
```
|
| 35 |
|
| 36 |
|
| 37 |
+
## About the Model
|
| 38 |
+
|
| 39 |
+
This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it.
|
| 40 |
+
|
| 41 |
+
The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels.
|
| 42 |
+
|
| 43 |
+
The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
|
| 44 |
+
I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
|
| 45 |
+
```
|
| 46 |
+
hyperparameters = {
|
| 47 |
+
"device": "gpu",
|
| 48 |
+
"seed": 1234,
|
| 49 |
+
"num_policies": 2,
|
| 50 |
+
"async_rl": true,
|
| 51 |
+
"serial_mode": false,
|
| 52 |
+
"batched_sampling": true,
|
| 53 |
+
"num_batches_to_accumulate": 2,
|
| 54 |
+
"worker_num_splits": 1,
|
| 55 |
+
"policy_workers_per_policy": 1,
|
| 56 |
+
"max_policy_lag": 1000,
|
| 57 |
+
"num_workers": 16,
|
| 58 |
+
"num_envs_per_worker": 2,
|
| 59 |
+
"batch_size": 1024,
|
| 60 |
+
"num_batches_per_epoch": 8,
|
| 61 |
+
"num_epochs": 4,
|
| 62 |
+
"rollout": 128,
|
| 63 |
+
"recurrence": 1,
|
| 64 |
+
"shuffle_minibatches": false,
|
| 65 |
+
"gamma": 0.99,
|
| 66 |
+
"reward_scale": 1.0,
|
| 67 |
+
"reward_clip": 1000.0,
|
| 68 |
+
"value_bootstrap": false,
|
| 69 |
+
"normalize_returns": true,
|
| 70 |
+
"exploration_loss_coeff": 0.0004677351413,
|
| 71 |
+
"value_loss_coeff": 0.5,
|
| 72 |
+
"kl_loss_coeff": 0.0,
|
| 73 |
+
"exploration_loss": "entropy",
|
| 74 |
+
"gae_lambda": 0.95,
|
| 75 |
+
"ppo_clip_ratio": 0.1,
|
| 76 |
+
"ppo_clip_value": 1.0,
|
| 77 |
+
"with_vtrace": false,
|
| 78 |
+
"vtrace_rho": 1.0,
|
| 79 |
+
"vtrace_c": 1.0,
|
| 80 |
+
"optimizer": "adam",
|
| 81 |
+
"adam_eps": 1e-05,
|
| 82 |
+
"adam_beta1": 0.9,
|
| 83 |
+
"adam_beta2": 0.999,
|
| 84 |
+
"max_grad_norm": 0.0,
|
| 85 |
+
"learning_rate": 0.0003033891184,
|
| 86 |
+
"lr_schedule": "linear_decay",
|
| 87 |
+
"lr_schedule_kl_threshold": 0.008,
|
| 88 |
+
"lr_adaptive_min": 1e-06,
|
| 89 |
+
"lr_adaptive_max": 0.01,
|
| 90 |
+
"obs_subtract_mean": 0.0,
|
| 91 |
+
"obs_scale": 255.0,
|
| 92 |
+
"normalize_input": true,
|
| 93 |
+
"normalize_input_keys": [
|
| 94 |
+
"obs"
|
| 95 |
+
],
|
| 96 |
+
"decorrelate_experience_max_seconds": 0,
|
| 97 |
+
"decorrelate_envs_on_one_worker": true,
|
| 98 |
+
"actor_worker_gpus": [],
|
| 99 |
+
"set_workers_cpu_affinity": true,
|
| 100 |
+
"force_envs_single_thread": false,
|
| 101 |
+
"default_niceness": 0,
|
| 102 |
+
"log_to_file": true,
|
| 103 |
+
"experiment_summaries_interval": 3,
|
| 104 |
+
"flush_summaries_interval": 30,
|
| 105 |
+
"stats_avg": 100,
|
| 106 |
+
"summaries_use_frameskip": true,
|
| 107 |
+
"heartbeat_interval": 10,
|
| 108 |
+
"heartbeat_reporting_interval": 60,
|
| 109 |
+
"train_for_env_steps": 100000000,
|
| 110 |
+
"train_for_seconds": 10000000000,
|
| 111 |
+
"save_every_sec": 120,
|
| 112 |
+
"keep_checkpoints": 2,
|
| 113 |
+
"load_checkpoint_kind": "latest",
|
| 114 |
+
"save_milestones_sec": 1200,
|
| 115 |
+
"save_best_every_sec": 5,
|
| 116 |
+
"save_best_metric": "reward",
|
| 117 |
+
"save_best_after": 100000,
|
| 118 |
+
"benchmark": false,
|
| 119 |
+
"encoder_mlp_layers": [
|
| 120 |
+
512,
|
| 121 |
+
512
|
| 122 |
+
],
|
| 123 |
+
"encoder_conv_architecture": "convnet_atari",
|
| 124 |
+
"encoder_conv_mlp_layers": [
|
| 125 |
+
512
|
| 126 |
+
],
|
| 127 |
+
"use_rnn": false,
|
| 128 |
+
"rnn_size": 512,
|
| 129 |
+
"rnn_type": "gru",
|
| 130 |
+
"rnn_num_layers": 1,
|
| 131 |
+
"decoder_mlp_layers": [],
|
| 132 |
+
"nonlinearity": "relu",
|
| 133 |
+
"policy_initialization": "orthogonal",
|
| 134 |
+
"policy_init_gain": 1.0,
|
| 135 |
+
"actor_critic_share_weights": true,
|
| 136 |
+
"adaptive_stddev": false,
|
| 137 |
+
"continuous_tanh_scale": 0.0,
|
| 138 |
+
"initial_stddev": 1.0,
|
| 139 |
+
"use_env_info_cache": false,
|
| 140 |
+
"env_gpu_actions": false,
|
| 141 |
+
"env_gpu_observations": true,
|
| 142 |
+
"env_frameskip": 4,
|
| 143 |
+
"env_framestack": 4,
|
| 144 |
+
}
|
| 145 |
+
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
|
| 150 |
## Using the model
|
| 151 |
|
| 152 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
| 153 |
```
|
| 154 |
+
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_freeway --train_dir=./train_dir --experiment=APPO-atari_freeway
|
| 155 |
```
|
| 156 |
|
| 157 |
|
|
|
|
| 162 |
|
| 163 |
To continue training with this model, use the `train` script corresponding to this environment:
|
| 164 |
```
|
| 165 |
+
python -m sf_examples.atari.train_atari --algo=APPO --env=atari_freeway --train_dir=./train_dir --experiment=APPO-atari_freeway --restart_behavior=resume --train_for_env_steps=10000000000
|
| 166 |
```
|
| 167 |
|
| 168 |
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_000089472_91619328_reward_34.000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ebb7e1d4551b13a4d6d3fc583ea417bd120c8ace9687dd4c228f5e0a2b37dc
|
| 3 |
+
size 20703411
|
checkpoint_p0/checkpoint_000097216_99549184.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f8e8003190ddeeebd657a0fde84ebc8030b7b0c8c50cd19b4af9100479243a
|
| 3 |
+
size 20703747
|
checkpoint_p0/checkpoint_000097664_100007936.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7f47b7e0d073920746bafba5ba1b42013aaf978e59ac542e7e23566f46b7ab4
|
| 3 |
+
size 20703747
|
checkpoint_p0/milestones/checkpoint_000007104_7274496.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fddb61f6761a1ac37f4e4ee4ef1224588aa33f873dc42d3df0119f87f4914314
|
| 3 |
+
size 20704603
|
checkpoint_p0/milestones/checkpoint_000014304_14647296.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba2ef8a2aa131fc66891bb7ff86d43528ad680d6e5d784c257f1ed746f6dfd4
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000021504_22020096.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02f1caa3ba5073d611fde0e99901334b06f9089d435a98627caaf4973f1cef7f
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000028736_29425664.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a685ef90fa6a26d867953cbc9ab32926da3964b84414649b4ec0d90c1ad2e6f
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000035936_36798464.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9e4153dcf27235d99b10adb47754298859447123a3dafb249359b0035fe1be7
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000043168_44204032.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7b0b94e9200b150280a355f6113b9c84814a21cbb59989a870b3b6a68fb4dd5
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000050368_51576832.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31d77ef252e1f22450ee6eef3d616753a449ab44a509a0da22cf423ad19b2700
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000057568_58949632.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0d70d57e1e7189d37dbd0864dffeb12f5845cc09b8364e7a4a3980264870653
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000064768_66322432.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7055462837c24c56d2124ea3cb5be2377240d219fa1d7c85120c91de50b6f2d
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000071968_73695232.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edfb97578f6b7ecb02f8f0c42c08261f30053ed4d633e23b716c212eff64e3fb
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000079200_81100800.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1e8cfbfdf405090790cf3e0e86ff7623d7d1eed403c83cc6e3d21690882450e
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000086432_88506368.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff5e010407af94a0906c3a59f3461af4b662e0a4080ee1fedcd9c38a0f5206e8
|
| 3 |
+
size 20704659
|
checkpoint_p0/milestones/checkpoint_000093632_95879168.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03272cb5c3192a03eafc16fcbf882347acc167db4d04350642b91cd105e8296f
|
| 3 |
+
size 20704659
|
checkpoint_p1/best_000097280_99614720_reward_34.000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebbac0a0c33123d1966083dad3d4be6fa336b8b9b29899d068fd03813da3af7c
|
| 3 |
+
size 20703411
|
checkpoint_p1/checkpoint_000097792_100139008.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06bcadee2c6225dee90561343d9e59abe379b47730a1badad9db6788008d1fa0
|
| 3 |
+
size 20703747
|
checkpoint_p1/checkpoint_000098272_100630528.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d96a8b072c5df17d3b13aab577cbb6e842c21e976bfaa1663b00282653e42622
|
| 3 |
+
size 20703747
|
checkpoint_p1/milestones/checkpoint_000007136_7307264.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1714a2c8a75b68498ab6d6b8b0172007b213002bf81020bac997dc4410ac676a
|
| 3 |
+
size 20704603
|
checkpoint_p1/milestones/checkpoint_000014400_14745600.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8914e758604688dc8f56c568b9c57fb55b95fe3ba1bebc7fd8e8435a9b60eb39
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000021664_22183936.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29120b4c5c471bd9a7bd6c107c3b1c014161d3ced8f7ebde35b18099e0dcf2d0
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000028896_29589504.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a8a1ebe8e017ace806015b6691e6bb14279e6c183808bce5f501140dcb6dc32
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000036160_37027840.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7570f05f51a38ee33a64a3b80e70eea8c32b82dec02bcb0383adfbd9ad9b661
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000043392_44433408.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc953ee20daeedd122d1508ecb6e9055a031b16998cbf895b8347ec9a02dda51
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000050656_51871744.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2079ab1492826f1a852d55045e314be3569f604261b5f9f01ed6ebf8e61b9476
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000057920_59310080.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efbb376b60d9849ea6fd2dd11572096d65e8f80b13cb96924b553c96e472f921
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000065152_66715648.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e37ccb2bcd56bd11d42f8c79340a71182a0e29e628e7accb55ebe0ddc98d575
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000072416_74153984.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa4b52d1516423a1e61318c5a39b2957c25c10db6cb242f565d38c529eeda002
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000079680_81592320.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7152b4c21ddf753962e1d32ef714c8a42ef198f6692c548dd2fbf64724459014
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000086912_88997888.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86ae18cd85272bc5a305cfb961391122400e976ad81aba1e7e7d11968c142c9d
|
| 3 |
+
size 20704659
|
checkpoint_p1/milestones/checkpoint_000094176_96436224.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0608a36d02bec0098f8ff01ac581c4afd1fa7e665662a34c53a360561123ce0f
|
| 3 |
+
size 20704659
|
config.json
CHANGED
|
@@ -2,23 +2,23 @@
|
|
| 2 |
"help": false,
|
| 3 |
"algo": "APPO",
|
| 4 |
"env": "atari_freeway",
|
| 5 |
-
"experiment": "
|
| 6 |
"train_dir": "./train_atari",
|
| 7 |
-
"restart_behavior": "
|
| 8 |
"device": "gpu",
|
| 9 |
-
"seed":
|
| 10 |
"num_policies": 2,
|
| 11 |
-
"async_rl":
|
| 12 |
"serial_mode": false,
|
| 13 |
-
"batched_sampling":
|
| 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":
|
| 19 |
-
"num_envs_per_worker":
|
| 20 |
-
"batch_size":
|
| 21 |
-
"num_batches_per_epoch":
|
| 22 |
"num_epochs": 4,
|
| 23 |
"rollout": 128,
|
| 24 |
"recurrence": 1,
|
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"reward_clip": 1000.0,
|
| 29 |
"value_bootstrap": false,
|
| 30 |
"normalize_returns": true,
|
| 31 |
-
"exploration_loss_coeff": 0.
|
| 32 |
"value_loss_coeff": 0.5,
|
| 33 |
"kl_loss_coeff": 0.0,
|
| 34 |
"exploration_loss": "entropy",
|
|
@@ -42,8 +42,8 @@
|
|
| 42 |
"adam_eps": 1e-05,
|
| 43 |
"adam_beta1": 0.9,
|
| 44 |
"adam_beta2": 0.999,
|
| 45 |
-
"max_grad_norm": 0.
|
| 46 |
-
"learning_rate": 0.
|
| 47 |
"lr_schedule": "linear_decay",
|
| 48 |
"lr_schedule_kl_threshold": 0.008,
|
| 49 |
"lr_adaptive_min": 1e-06,
|
|
@@ -51,7 +51,9 @@
|
|
| 51 |
"obs_subtract_mean": 0.0,
|
| 52 |
"obs_scale": 255.0,
|
| 53 |
"normalize_input": true,
|
| 54 |
-
"normalize_input_keys":
|
|
|
|
|
|
|
| 55 |
"decorrelate_experience_max_seconds": 0,
|
| 56 |
"decorrelate_envs_on_one_worker": true,
|
| 57 |
"actor_worker_gpus": [],
|
|
@@ -63,14 +65,14 @@
|
|
| 63 |
"flush_summaries_interval": 30,
|
| 64 |
"stats_avg": 100,
|
| 65 |
"summaries_use_frameskip": true,
|
| 66 |
-
"heartbeat_interval":
|
| 67 |
-
"heartbeat_reporting_interval":
|
| 68 |
-
"train_for_env_steps":
|
| 69 |
"train_for_seconds": 10000000000,
|
| 70 |
"save_every_sec": 120,
|
| 71 |
"keep_checkpoints": 2,
|
| 72 |
"load_checkpoint_kind": "latest",
|
| 73 |
-
"save_milestones_sec":
|
| 74 |
"save_best_every_sec": 5,
|
| 75 |
"save_best_metric": "reward",
|
| 76 |
"save_best_after": 100000,
|
|
@@ -104,7 +106,7 @@
|
|
| 104 |
"use_record_episode_statistics": true,
|
| 105 |
"with_wandb": true,
|
| 106 |
"wandb_user": "matt-stammers",
|
| 107 |
-
"wandb_project": "
|
| 108 |
"wandb_group": "atari_freeway",
|
| 109 |
"wandb_job_type": "SF",
|
| 110 |
"wandb_tags": [
|
|
@@ -122,16 +124,32 @@
|
|
| 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_freeway --experiment=
|
| 126 |
"cli_args": {
|
| 127 |
"algo": "APPO",
|
| 128 |
"env": "atari_freeway",
|
| 129 |
-
"experiment": "
|
| 130 |
"train_dir": "./train_atari",
|
|
|
|
|
|
|
| 131 |
"num_policies": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
"with_wandb": true,
|
| 133 |
"wandb_user": "matt-stammers",
|
| 134 |
-
"wandb_project": "
|
| 135 |
"wandb_group": "atari_freeway",
|
| 136 |
"wandb_job_type": "SF",
|
| 137 |
"wandb_tags": [
|
|
@@ -140,5 +158,5 @@
|
|
| 140 |
},
|
| 141 |
"git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
|
| 142 |
"git_repo_name": "not a git repository",
|
| 143 |
-
"wandb_unique_id": "
|
| 144 |
}
|
|
|
|
| 2 |
"help": false,
|
| 3 |
"algo": "APPO",
|
| 4 |
"env": "atari_freeway",
|
| 5 |
+
"experiment": "atari_freeway_APPO",
|
| 6 |
"train_dir": "./train_atari",
|
| 7 |
+
"restart_behavior": "restart",
|
| 8 |
"device": "gpu",
|
| 9 |
+
"seed": 1234,
|
| 10 |
"num_policies": 2,
|
| 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": 16,
|
| 19 |
+
"num_envs_per_worker": 2,
|
| 20 |
+
"batch_size": 1024,
|
| 21 |
+
"num_batches_per_epoch": 8,
|
| 22 |
"num_epochs": 4,
|
| 23 |
"rollout": 128,
|
| 24 |
"recurrence": 1,
|
|
|
|
| 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",
|
|
|
|
| 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,
|
|
|
|
| 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": 0,
|
| 58 |
"decorrelate_envs_on_one_worker": true,
|
| 59 |
"actor_worker_gpus": [],
|
|
|
|
| 65 |
"flush_summaries_interval": 30,
|
| 66 |
"stats_avg": 100,
|
| 67 |
"summaries_use_frameskip": true,
|
| 68 |
+
"heartbeat_interval": 10,
|
| 69 |
+
"heartbeat_reporting_interval": 60,
|
| 70 |
+
"train_for_env_steps": 100000000,
|
| 71 |
"train_for_seconds": 10000000000,
|
| 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,
|
|
|
|
| 106 |
"use_record_episode_statistics": true,
|
| 107 |
"with_wandb": true,
|
| 108 |
"wandb_user": "matt-stammers",
|
| 109 |
+
"wandb_project": "atari_APPO",
|
| 110 |
"wandb_group": "atari_freeway",
|
| 111 |
"wandb_job_type": "SF",
|
| 112 |
"wandb_tags": [
|
|
|
|
| 124 |
"pbt_target_objective": "true_objective",
|
| 125 |
"pbt_perturb_min": 1.1,
|
| 126 |
"pbt_perturb_max": 1.5,
|
| 127 |
+
"command_line": "--algo=APPO --env=atari_freeway --experiment=atari_freeway_APPO --num_policies=2 --restart_behavior=restart --train_dir=./train_atari --train_for_env_steps=100000000 --seed=1234 --num_workers=16 --num_envs_per_worker=2 --num_batches_per_epoch=8 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_freeway --wandb_job_type=SF --wandb_tags=atari",
|
| 128 |
"cli_args": {
|
| 129 |
"algo": "APPO",
|
| 130 |
"env": "atari_freeway",
|
| 131 |
+
"experiment": "atari_freeway_APPO",
|
| 132 |
"train_dir": "./train_atari",
|
| 133 |
+
"restart_behavior": "restart",
|
| 134 |
+
"seed": 1234,
|
| 135 |
"num_policies": 2,
|
| 136 |
+
"async_rl": true,
|
| 137 |
+
"batched_sampling": true,
|
| 138 |
+
"num_workers": 16,
|
| 139 |
+
"num_envs_per_worker": 2,
|
| 140 |
+
"batch_size": 1024,
|
| 141 |
+
"num_batches_per_epoch": 8,
|
| 142 |
+
"num_epochs": 4,
|
| 143 |
+
"exploration_loss_coeff": 0.0004677351413,
|
| 144 |
+
"max_grad_norm": 0.0,
|
| 145 |
+
"learning_rate": 0.0003033891184,
|
| 146 |
+
"heartbeat_interval": 10,
|
| 147 |
+
"heartbeat_reporting_interval": 60,
|
| 148 |
+
"train_for_env_steps": 100000000,
|
| 149 |
+
"save_milestones_sec": 1200,
|
| 150 |
"with_wandb": true,
|
| 151 |
"wandb_user": "matt-stammers",
|
| 152 |
+
"wandb_project": "atari_APPO",
|
| 153 |
"wandb_group": "atari_freeway",
|
| 154 |
"wandb_job_type": "SF",
|
| 155 |
"wandb_tags": [
|
|
|
|
| 158 |
},
|
| 159 |
"git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
|
| 160 |
"git_repo_name": "not a git repository",
|
| 161 |
+
"wandb_unique_id": "atari_freeway_APPO_20231011_101641_307643"
|
| 162 |
}
|
git.diff
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 sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
|
| 3 |
+
size 14426734
|
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:fe24b246f3e9b2d760424f65a4c3860f17bf503131d8e8ae8bab07ce1735597d
|
| 3 |
+
size 6947894
|
sf_log.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|