First Push
Browse files- SnowballTarget.onnx +2 -2
- SnowballTarget/SnowballTarget-149984.onnx +2 -2
- SnowballTarget/SnowballTarget-149984.pt +2 -2
- SnowballTarget/SnowballTarget-199984.onnx +2 -2
- SnowballTarget/SnowballTarget-199984.pt +2 -2
- SnowballTarget/SnowballTarget-200112.onnx +2 -2
- SnowballTarget/SnowballTarget-200112.pt +2 -2
- SnowballTarget/SnowballTarget-49936.onnx +2 -2
- SnowballTarget/SnowballTarget-49936.pt +2 -2
- SnowballTarget/SnowballTarget-99960.onnx +2 -2
- SnowballTarget/SnowballTarget-99960.pt +2 -2
- SnowballTarget/checkpoint.pt +2 -2
- SnowballTarget/events.out.tfevents.1716710689.9bd833adf9b7.9473.0 +3 -0
- config.json +1 -1
- configuration.yaml +4 -4
- run_logs/Player-0.log +5 -8
- run_logs/timers.json +112 -112
- run_logs/training_status.json +24 -24
SnowballTarget.onnx
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:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-149984.onnx
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 sha256:4087d4a7a0ed98d1e30efb9f197837917e8f2d9c97288fc76ef1e18ce28ab7c1
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-149984.pt
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 sha256:8d00c4fb53bba706a4ee1412a2ecf30b59ebb95b44cde3717405557ec17acb9a
|
3 |
+
size 1143083
|
SnowballTarget/SnowballTarget-199984.onnx
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:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-199984.pt
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:e59e3b48b3632af015dc6a38d494f7012193f598d910e738054d7cd6ed1f7986
|
3 |
+
size 1143083
|
SnowballTarget/SnowballTarget-200112.onnx
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:e70e734b200138695e2c3013c6b01ea46b0bdbfb789cd6a2d914b5c2a22159a5
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-200112.pt
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:f7fb6ef6b172f1eadbff31c6925e4513ba82008335bb9b4424bb74f0c71185b3
|
3 |
+
size 1143083
|
SnowballTarget/SnowballTarget-49936.onnx
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 sha256:3f59101234824e69a1e30affe873939cf91feda1d9569ad4d6337f5454908aee
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-49936.pt
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 sha256:8a936a93043a0c9f56609711c4cb61cdaa67e9ac49e516318031b192dce4f190
|
3 |
+
size 1143024
|
SnowballTarget/SnowballTarget-99960.onnx
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 sha256:9a72c03cf6ff0266f090beada747ed9b9b8f77bf7d4dd8f705d08eca0b624d21
|
3 |
+
size 197609
|
SnowballTarget/SnowballTarget-99960.pt
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 sha256:93eee4b58a589ec491dc73f7f02cdd7610b814c9ec78b12e7412f3ec6606568b
|
3 |
+
size 1143024
|
SnowballTarget/checkpoint.pt
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 sha256:9dffe09e55ac946610eff28dadb707e1fb3fefda92474971427adbf8ff6b69ef
|
3 |
+
size 1142434
|
SnowballTarget/events.out.tfevents.1716710689.9bd833adf9b7.9473.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:217d3c2ee94f27aa8c2318268fd87c7d3f127f059423550d7a1040c4b183e372
|
3 |
+
size 23378
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0006, "beta": 0.005, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 1, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
@@ -5,9 +5,9 @@ behaviors:
|
|
5 |
hyperparameters:
|
6 |
batch_size: 128
|
7 |
buffer_size: 2048
|
8 |
-
learning_rate: 0.
|
9 |
beta: 0.005
|
10 |
-
epsilon: 0.
|
11 |
lambd: 0.95
|
12 |
num_epoch: 3
|
13 |
shared_critic: false
|
@@ -18,7 +18,7 @@ behaviors:
|
|
18 |
network_settings:
|
19 |
normalize: false
|
20 |
hidden_units: 128
|
21 |
-
num_layers:
|
22 |
vis_encode_type: simple
|
23 |
memory: null
|
24 |
goal_conditioning_type: hyper
|
@@ -66,7 +66,7 @@ engine_settings:
|
|
66 |
no_graphics_monitor: false
|
67 |
environment_parameters: null
|
68 |
checkpoint_settings:
|
69 |
-
run_id:
|
70 |
initialize_from: null
|
71 |
load_model: false
|
72 |
resume: false
|
|
|
5 |
hyperparameters:
|
6 |
batch_size: 128
|
7 |
buffer_size: 2048
|
8 |
+
learning_rate: 0.0006
|
9 |
beta: 0.005
|
10 |
+
epsilon: 0.3
|
11 |
lambd: 0.95
|
12 |
num_epoch: 3
|
13 |
shared_critic: false
|
|
|
18 |
network_settings:
|
19 |
normalize: false
|
20 |
hidden_units: 128
|
21 |
+
num_layers: 1
|
22 |
vis_encode_type: simple
|
23 |
memory: null
|
24 |
goal_conditioning_type: hyper
|
|
|
66 |
no_graphics_monitor: false
|
67 |
environment_parameters: null
|
68 |
checkpoint_settings:
|
69 |
+
run_id: SnowballTarget2
|
70 |
initialize_from: null
|
71 |
load_model: false
|
72 |
resume: false
|
run_logs/Player-0.log
CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
|
|
2 |
Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
|
3 |
Preloaded 'lib_burst_generated.so'
|
4 |
Preloaded 'libgrpc_csharp_ext.x64.so'
|
5 |
-
PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
|
6 |
-
PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
|
7 |
-
Unable to load player prefs
|
8 |
Initialize engine version: 2021.3.14f1 (eee1884e7226)
|
9 |
[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
|
10 |
Forcing GfxDevice: Null
|
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
|
|
34 |
FMOD failed to initialize the output device.: "Error initializing output device. " (60)
|
35 |
FMOD initialized on nosound output
|
36 |
Begin MonoManager ReloadAssembly
|
37 |
-
- Completed reload, in 0.
|
38 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
39 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
40 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
|
|
45 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
46 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
47 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
48 |
-
UnloadTime: 0.
|
49 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
50 |
requesting resize 84 x 84
|
51 |
Setting up 1 worker threads for Enlighten.
|
@@ -169,7 +166,7 @@ Memory Statistics:
|
|
169 |
Peak Allocated Bytes 0 B
|
170 |
Overflow Count 0
|
171 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
172 |
-
Peak main deferred allocation count
|
173 |
[ALLOC_BUCKET]
|
174 |
Large Block size 4.0 MB
|
175 |
Used Block count 1
|
@@ -184,7 +181,7 @@ Memory Statistics:
|
|
184 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
|
185 |
Requested Block Size 16.0 MB
|
186 |
Peak Block count 1
|
187 |
-
Peak Allocated memory 17.
|
188 |
Peak Large allocation bytes 16.0 MB
|
189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
190 |
Initial Block Size 2.0 MB
|
@@ -213,7 +210,7 @@ Memory Statistics:
|
|
213 |
Used Block count 1
|
214 |
Peak Allocated bytes 1.0 MB
|
215 |
[ALLOC_GFX_MAIN]
|
216 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
217 |
Requested Block Size 16.0 MB
|
218 |
Peak Block count 1
|
219 |
Peak Allocated memory 68.2 KB
|
|
|
2 |
Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
|
3 |
Preloaded 'lib_burst_generated.so'
|
4 |
Preloaded 'libgrpc_csharp_ext.x64.so'
|
|
|
|
|
|
|
5 |
Initialize engine version: 2021.3.14f1 (eee1884e7226)
|
6 |
[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
|
7 |
Forcing GfxDevice: Null
|
|
|
31 |
FMOD failed to initialize the output device.: "Error initializing output device. " (60)
|
32 |
FMOD initialized on nosound output
|
33 |
Begin MonoManager ReloadAssembly
|
34 |
+
- Completed reload, in 0.088 seconds
|
35 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
36 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
37 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
|
42 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
43 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
44 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
45 |
+
UnloadTime: 0.817515 ms
|
46 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
47 |
requesting resize 84 x 84
|
48 |
Setting up 1 worker threads for Enlighten.
|
|
|
166 |
Peak Allocated Bytes 0 B
|
167 |
Overflow Count 0
|
168 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
169 |
+
Peak main deferred allocation count 42
|
170 |
[ALLOC_BUCKET]
|
171 |
Large Block size 4.0 MB
|
172 |
Used Block count 1
|
|
|
181 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
|
182 |
Requested Block Size 16.0 MB
|
183 |
Peak Block count 1
|
184 |
+
Peak Allocated memory 17.4 MB
|
185 |
Peak Large allocation bytes 16.0 MB
|
186 |
[ALLOC_TEMP_JOB_1_FRAME]
|
187 |
Initial Block Size 2.0 MB
|
|
|
210 |
Used Block count 1
|
211 |
Peak Allocated bytes 1.0 MB
|
212 |
[ALLOC_GFX_MAIN]
|
213 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 4437 frames, [64.0 KB-128.0 KB]: 1023 frames
|
214 |
Requested Block Size 16.0 MB
|
215 |
Peak Block count 1
|
216 |
Peak Allocated memory 68.2 KB
|
run_logs/timers.json
CHANGED
@@ -2,15 +2,15 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
-
"value":
|
6 |
-
"min":
|
7 |
-
"max": 2.
|
8 |
"count": 20
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
"count": 20
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
@@ -26,15 +26,15 @@
|
|
26 |
"count": 20
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
-
"value":
|
30 |
-
"min": 0.
|
31 |
-
"max":
|
32 |
"count": 20
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
"count": 20
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
@@ -50,51 +50,51 @@
|
|
50 |
"count": 20
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
-
"value": 0.
|
54 |
-
"min": 0.
|
55 |
-
"max": 0.
|
56 |
"count": 20
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
-
"value": 0.
|
60 |
-
"min": 0.
|
61 |
-
"max": 0.
|
62 |
"count": 20
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
-
"value": 0.
|
66 |
-
"min": 0.
|
67 |
-
"max": 0.
|
68 |
"count": 20
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
-
"value": 0.
|
72 |
-
"min": 0.
|
73 |
-
"max": 1.
|
74 |
"count": 20
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
-
"value":
|
78 |
-
"min":
|
79 |
-
"max": 0.
|
80 |
"count": 20
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
-
"value":
|
84 |
-
"min":
|
85 |
-
"max": 0.
|
86 |
"count": 20
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": 0.
|
91 |
-
"max": 0.
|
92 |
"count": 20
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
-
"value": 0.
|
96 |
-
"min": 0.
|
97 |
-
"max":
|
98 |
"count": 20
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
@@ -110,27 +110,27 @@
|
|
110 |
"count": 20
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
-
"value":
|
114 |
-
"min": 3.
|
115 |
-
"max":
|
116 |
"count": 20
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
-
"value":
|
120 |
-
"min":
|
121 |
-
"max":
|
122 |
"count": 20
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
-
"value":
|
126 |
-
"min": 3.
|
127 |
-
"max":
|
128 |
"count": 20
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
-
"value":
|
132 |
-
"min":
|
133 |
-
"max":
|
134 |
"count": 20
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
@@ -148,67 +148,67 @@
|
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
-
"start_time_seconds": "
|
152 |
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
|
153 |
-
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=
|
154 |
"mlagents_version": "1.1.0.dev0",
|
155 |
"mlagents_envs_version": "1.1.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "2.3.0+cu121",
|
158 |
"numpy_version": "1.23.5",
|
159 |
-
"end_time_seconds": "
|
160 |
},
|
161 |
-
"total":
|
162 |
"count": 1,
|
163 |
-
"self": 0.
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
-
"total": 0.
|
167 |
"count": 1,
|
168 |
-
"self": 0.
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
-
"total":
|
172 |
"count": 1,
|
173 |
-
"self": 0.
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
-
"total":
|
177 |
"count": 1,
|
178 |
-
"self":
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
-
"total":
|
182 |
"count": 18200,
|
183 |
-
"self": 0.
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
-
"total":
|
187 |
"count": 18200,
|
188 |
-
"self":
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
-
"total":
|
192 |
"count": 18200,
|
193 |
-
"self": 1.
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
-
"total":
|
197 |
"count": 18200,
|
198 |
-
"self":
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
-
"total": 0.
|
204 |
"count": 18200,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
-
"total":
|
209 |
"count": 18200,
|
210 |
"is_parallel": true,
|
211 |
-
"self":
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
@@ -217,48 +217,48 @@
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
-
"total": 0.
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
-
"self": 0.
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
-
"total": 0.
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
-
"self": 0.
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
-
"total": 0.
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
-
"self": 0.
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
-
"total": 0.
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
-
"self": 0.
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
-
"total": 0.
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
-
"self": 0.
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
-
"total": 0.
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
-
"self": 0.
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
-
"total": 0.
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
-
"self": 0.
|
262 |
}
|
263 |
}
|
264 |
}
|
@@ -267,34 +267,34 @@
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
-
"total":
|
271 |
"count": 18199,
|
272 |
"is_parallel": true,
|
273 |
-
"self": 11.
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
-
"total": 6.
|
277 |
"count": 18199,
|
278 |
"is_parallel": true,
|
279 |
-
"self": 6.
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
-
"total":
|
283 |
"count": 18199,
|
284 |
"is_parallel": true,
|
285 |
-
"self":
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
-
"total":
|
289 |
"count": 18199,
|
290 |
"is_parallel": true,
|
291 |
-
"self": 7.
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
-
"total":
|
295 |
"count": 181990,
|
296 |
"is_parallel": true,
|
297 |
-
"self":
|
298 |
}
|
299 |
}
|
300 |
}
|
@@ -309,9 +309,9 @@
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
-
"total":
|
313 |
"count": 1,
|
314 |
-
"self":
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
@@ -320,36 +320,36 @@
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
-
"total":
|
324 |
-
"count":
|
325 |
"is_parallel": true,
|
326 |
-
"self":
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
-
"total":
|
330 |
-
"count":
|
331 |
"is_parallel": true,
|
332 |
-
"self":
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
-
"total": 0.
|
336 |
"count": 4,
|
337 |
"is_parallel": true,
|
338 |
-
"self": 0.
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
-
"total":
|
344 |
"count": 90,
|
345 |
"is_parallel": true,
|
346 |
-
"self":
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
-
"total":
|
350 |
"count": 4587,
|
351 |
"is_parallel": true,
|
352 |
-
"self":
|
353 |
}
|
354 |
}
|
355 |
}
|
@@ -360,14 +360,14 @@
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
-
"total": 0.
|
364 |
"count": 1,
|
365 |
-
"self": 0.
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
-
"total": 0.
|
369 |
"count": 1,
|
370 |
-
"self": 0.
|
371 |
}
|
372 |
}
|
373 |
}
|
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
+
"value": 1.0069396495819092,
|
6 |
+
"min": 1.0069396495819092,
|
7 |
+
"max": 2.810028076171875,
|
8 |
"count": 20
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
+
"value": 9614.259765625,
|
12 |
+
"min": 9614.259765625,
|
13 |
+
"max": 28808.408203125,
|
14 |
"count": 20
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
|
|
26 |
"count": 20
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 12.656725883483887,
|
30 |
+
"min": 0.31081098318099976,
|
31 |
+
"max": 12.656725883483887,
|
32 |
"count": 20
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 2468.0615234375,
|
36 |
+
"min": 60.297332763671875,
|
37 |
+
"max": 2568.51611328125,
|
38 |
"count": 20
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
|
50 |
"count": 20
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.06861288506586467,
|
54 |
+
"min": 0.057799714654524284,
|
55 |
+
"max": 0.0758767314015559,
|
56 |
"count": 20
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.2744515402634587,
|
60 |
+
"min": 0.23119885861809714,
|
61 |
+
"max": 0.36978030635623776,
|
62 |
"count": 20
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.23546830710827138,
|
66 |
+
"min": 0.1087834547700671,
|
67 |
+
"max": 0.281679127146216,
|
68 |
"count": 20
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
+
"value": 0.9418732284330855,
|
72 |
+
"min": 0.4351338190802684,
|
73 |
+
"max": 1.4048231445691166,
|
74 |
"count": 20
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
+
"value": 1.616409730600001e-05,
|
78 |
+
"min": 1.616409730600001e-05,
|
79 |
+
"max": 0.0005837640027059999,
|
80 |
"count": 20
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
+
"value": 6.465638922400003e-05,
|
84 |
+
"min": 6.465638922400003e-05,
|
85 |
+
"max": 0.00277032003828,
|
86 |
"count": 20
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.10538800000000001,
|
90 |
+
"min": 0.10538800000000001,
|
91 |
+
"max": 0.29458799999999996,
|
92 |
"count": 20
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
+
"value": 0.42155200000000004,
|
96 |
+
"min": 0.42155200000000004,
|
97 |
+
"max": 1.42344,
|
98 |
"count": 20
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
|
|
110 |
"count": 20
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
+
"value": 24.681818181818183,
|
114 |
+
"min": 3.1136363636363638,
|
115 |
+
"max": 24.963636363636365,
|
116 |
"count": 20
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
+
"value": 1086.0,
|
120 |
+
"min": 137.0,
|
121 |
+
"max": 1373.0,
|
122 |
"count": 20
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
+
"value": 24.681818181818183,
|
126 |
+
"min": 3.1136363636363638,
|
127 |
+
"max": 24.963636363636365,
|
128 |
"count": 20
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
+
"value": 1086.0,
|
132 |
+
"min": 137.0,
|
133 |
+
"max": 1373.0,
|
134 |
"count": 20
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
|
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1716710688",
|
152 |
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
|
153 |
+
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
|
154 |
"mlagents_version": "1.1.0.dev0",
|
155 |
"mlagents_envs_version": "1.1.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "2.3.0+cu121",
|
158 |
"numpy_version": "1.23.5",
|
159 |
+
"end_time_seconds": "1716711189"
|
160 |
},
|
161 |
+
"total": 500.79940837000004,
|
162 |
"count": 1,
|
163 |
+
"self": 0.47871936000046844,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.05563367099966854,
|
167 |
"count": 1,
|
168 |
+
"self": 0.05563367099966854
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 500.2650553389999,
|
172 |
"count": 1,
|
173 |
+
"self": 0.7109024630158274,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 2.115907714000059,
|
177 |
"count": 1,
|
178 |
+
"self": 2.115907714000059
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 497.35660923498426,
|
182 |
"count": 18200,
|
183 |
+
"self": 0.3631436589657824,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 496.9934655760185,
|
187 |
"count": 18200,
|
188 |
+
"self": 326.54533360395635,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 170.0980387850159,
|
192 |
"count": 18200,
|
193 |
+
"self": 1.7037756250006169,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 168.39426316001527,
|
197 |
"count": 18200,
|
198 |
+
"self": 168.39426316001527
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
+
"total": 0.35009318704624093,
|
204 |
"count": 18200,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
+
"total": 498.7785037659978,
|
209 |
"count": 18200,
|
210 |
"is_parallel": true,
|
211 |
+
"self": 243.94271257897435,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
+
"total": 0.002219015999799012,
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
+
"self": 0.0006655649990534585,
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
+
"total": 0.0015534510007455538,
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
+
"self": 0.0015534510007455538
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
+
"total": 0.06019268000000011,
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.0007173359999796958,
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
+
"total": 0.0004115980000278796,
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
+
"self": 0.0004115980000278796
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
+
"total": 0.05698251200010418,
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.05698251200010418
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
+
"total": 0.0020812339998883544,
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.00039561100038554287,
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
+
"total": 0.0016856229995028116,
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 0.0016856229995028116
|
262 |
}
|
263 |
}
|
264 |
}
|
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
+
"total": 254.83579118702346,
|
271 |
"count": 18199,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 11.347686508004244,
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
+
"total": 6.006531404995712,
|
277 |
"count": 18199,
|
278 |
"is_parallel": true,
|
279 |
+
"self": 6.006531404995712
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
+
"total": 200.15692748401852,
|
283 |
"count": 18199,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 200.15692748401852
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
+
"total": 37.32464579000498,
|
289 |
"count": 18199,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 7.39685486497774,
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
+
"total": 29.92779092502724,
|
295 |
"count": 181990,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 29.92779092502724
|
298 |
}
|
299 |
}
|
300 |
}
|
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
+
"total": 0.00013762099979430786,
|
313 |
"count": 1,
|
314 |
+
"self": 0.00013762099979430786,
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
+
"total": 491.2628267113032,
|
324 |
+
"count": 711357,
|
325 |
"is_parallel": true,
|
326 |
+
"self": 15.55820723330362,
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
+
"total": 275.542963600999,
|
330 |
+
"count": 711357,
|
331 |
"is_parallel": true,
|
332 |
+
"self": 275.0221872739994,
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
+
"total": 0.5207763269995667,
|
336 |
"count": 4,
|
337 |
"is_parallel": true,
|
338 |
+
"self": 0.5207763269995667
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
+
"total": 200.1616558770006,
|
344 |
"count": 90,
|
345 |
"is_parallel": true,
|
346 |
+
"self": 62.33664410699612,
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
+
"total": 137.8250117700045,
|
350 |
"count": 4587,
|
351 |
"is_parallel": true,
|
352 |
+
"self": 137.8250117700045
|
353 |
}
|
354 |
}
|
355 |
}
|
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
+
"total": 0.08149830599995767,
|
364 |
"count": 1,
|
365 |
+
"self": 0.0008183389995792822,
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
+
"total": 0.08067996700037838,
|
369 |
"count": 1,
|
370 |
+
"self": 0.08067996700037838
|
371 |
}
|
372 |
}
|
373 |
}
|
run_logs/training_status.json
CHANGED
@@ -3,57 +3,57 @@
|
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
"steps": 49936,
|
6 |
-
"file_path": "results/
|
7 |
-
"reward":
|
8 |
-
"creation_time":
|
9 |
"auxillary_file_paths": [
|
10 |
-
"results/
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
"steps": 99960,
|
15 |
-
"file_path": "results/
|
16 |
-
"reward":
|
17 |
-
"creation_time":
|
18 |
"auxillary_file_paths": [
|
19 |
-
"results/
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
"steps": 149984,
|
24 |
-
"file_path": "results/
|
25 |
-
"reward":
|
26 |
-
"creation_time":
|
27 |
"auxillary_file_paths": [
|
28 |
-
"results/
|
29 |
]
|
30 |
},
|
31 |
{
|
32 |
"steps": 199984,
|
33 |
-
"file_path": "results/
|
34 |
-
"reward":
|
35 |
-
"creation_time":
|
36 |
"auxillary_file_paths": [
|
37 |
-
"results/
|
38 |
]
|
39 |
},
|
40 |
{
|
41 |
"steps": 200112,
|
42 |
-
"file_path": "results/
|
43 |
-
"reward":
|
44 |
-
"creation_time":
|
45 |
"auxillary_file_paths": [
|
46 |
-
"results/
|
47 |
]
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
"steps": 200112,
|
52 |
-
"file_path": "results/
|
53 |
-
"reward":
|
54 |
-
"creation_time":
|
55 |
"auxillary_file_paths": [
|
56 |
-
"results/
|
57 |
]
|
58 |
}
|
59 |
},
|
|
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
"steps": 49936,
|
6 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
|
7 |
+
"reward": 15.272727272727273,
|
8 |
+
"creation_time": 1716710816.7560582,
|
9 |
"auxillary_file_paths": [
|
10 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
"steps": 99960,
|
15 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
|
16 |
+
"reward": 21.818181818181817,
|
17 |
+
"creation_time": 1716710941.0128334,
|
18 |
"auxillary_file_paths": [
|
19 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
"steps": 149984,
|
24 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
|
25 |
+
"reward": 23.818181818181817,
|
26 |
+
"creation_time": 1716711064.1459694,
|
27 |
"auxillary_file_paths": [
|
28 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
|
29 |
]
|
30 |
},
|
31 |
{
|
32 |
"steps": 199984,
|
33 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
|
34 |
+
"reward": 24.272727272727273,
|
35 |
+
"creation_time": 1716711188.941713,
|
36 |
"auxillary_file_paths": [
|
37 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
|
38 |
]
|
39 |
},
|
40 |
{
|
41 |
"steps": 200112,
|
42 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
|
43 |
+
"reward": 24.272727272727273,
|
44 |
+
"creation_time": 1716711189.0530596,
|
45 |
"auxillary_file_paths": [
|
46 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
]
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
"steps": 200112,
|
52 |
+
"file_path": "results/SnowballTarget2/SnowballTarget.onnx",
|
53 |
+
"reward": 24.272727272727273,
|
54 |
+
"creation_time": 1716711189.0530596,
|
55 |
"auxillary_file_paths": [
|
56 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
|
57 |
]
|
58 |
}
|
59 |
},
|