add ppo snowballtarget agent
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/{SnowballTarget-1408.onnx → SnowballTarget-49936.onnx} +1 -1
- SnowballTarget/{SnowballTarget-1408.pt → SnowballTarget-49936.pt} +2 -2
- SnowballTarget/SnowballTarget-60104.onnx +3 -0
- SnowballTarget/SnowballTarget-60104.pt +3 -0
- SnowballTarget/checkpoint.pt +2 -2
- SnowballTarget/{events.out.tfevents.1680784150.f5f04898c26b.966.0 → events.out.tfevents.1680784929.50ee6e3d3587.973.0} +2 -2
- config.json +1 -1
- configuration.yaml +1 -1
- run_logs/Player-0.log +15 -15
- run_logs/timers.json +236 -68
- run_logs/training_status.json +18 -9
SnowballTarget.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 646532
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8853c2a028cef293a4cc786e8d35c60fc2e75117ad45527472a09bc755d98659
|
3 |
size 646532
|
SnowballTarget/{SnowballTarget-1408.onnx → SnowballTarget-49936.onnx}
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 646532
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b1a680c8a3eae1e9e55edd425b5a1e6863b81b739ef70d19e0980f445d423e4
|
3 |
size 646532
|
SnowballTarget/{SnowballTarget-1408.pt → SnowballTarget-49936.pt}
RENAMED
@@ -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 sha256:3b50b9f9d96ce559db17e730434d3bf0f16739b7bd35f1e8f21dda629853aed6
|
3 |
+
size 3843968
|
SnowballTarget/SnowballTarget-60104.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8853c2a028cef293a4cc786e8d35c60fc2e75117ad45527472a09bc755d98659
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-60104.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a540ceb8966198116d14f1762072fb5a81c12f8c52a3a9b4e5d6b55eb1a51385
|
3 |
+
size 3843968
|
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:a540ceb8966198116d14f1762072fb5a81c12f8c52a3a9b4e5d6b55eb1a51385
|
3 |
+
size 3843968
|
SnowballTarget/{events.out.tfevents.1680784150.f5f04898c26b.966.0 → events.out.tfevents.1680784929.50ee6e3d3587.973.0}
RENAMED
@@ -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 sha256:22a138270fb14b13d56b1586ed96d1043beb343bddff8362e7ab0af0353bd141
|
3 |
+
size 12355
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "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": 256, "num_layers": 2, "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":
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "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": 256, "num_layers": 2, "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": 60000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
@@ -38,7 +38,7 @@ behaviors:
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
-
max_steps:
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
+
max_steps: 60000
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
run_logs/Player-0.log
CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(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 +45,7 @@ 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.
|
@@ -53,7 +53,7 @@ Memory Statistics:
|
|
53 |
[ALLOC_TEMP_TLS] TLS Allocator
|
54 |
StackAllocators :
|
55 |
[ALLOC_TEMP_MAIN]
|
56 |
-
Peak usage frame count: [8.0 KB-16.0 KB]:
|
57 |
Initial Block Size 4.0 MB
|
58 |
Current Block Size 4.0 MB
|
59 |
Peak Allocated Bytes 2.0 MB
|
@@ -169,22 +169,22 @@ 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
|
176 |
Peak Allocated bytes 1.0 MB
|
177 |
[ALLOC_DEFAULT_MAIN]
|
178 |
-
Peak usage frame count: [4.0 MB-8.0 MB]:
|
179 |
Requested Block Size 16.0 MB
|
180 |
Peak Block count 1
|
181 |
-
Peak Allocated memory
|
182 |
Peak Large allocation bytes 0 B
|
183 |
[ALLOC_DEFAULT_THREAD]
|
184 |
-
Peak usage frame count: [16.0 MB-32.0 MB]:
|
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
|
@@ -213,13 +213,13 @@ 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
|
220 |
Peak Large allocation bytes 0 B
|
221 |
[ALLOC_GFX_THREAD]
|
222 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
223 |
Requested Block Size 16.0 MB
|
224 |
Peak Block count 1
|
225 |
Peak Allocated memory 39.6 KB
|
@@ -231,13 +231,13 @@ Memory Statistics:
|
|
231 |
Used Block count 1
|
232 |
Peak Allocated bytes 1.0 MB
|
233 |
[ALLOC_CACHEOBJECTS_MAIN]
|
234 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
235 |
Requested Block Size 4.0 MB
|
236 |
Peak Block count 1
|
237 |
Peak Allocated memory 0.6 MB
|
238 |
Peak Large allocation bytes 0 B
|
239 |
[ALLOC_CACHEOBJECTS_THREAD]
|
240 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
241 |
Requested Block Size 4.0 MB
|
242 |
Peak Block count 1
|
243 |
Peak Allocated memory 2.2 MB
|
@@ -249,13 +249,13 @@ Memory Statistics:
|
|
249 |
Used Block count 1
|
250 |
Peak Allocated bytes 1.0 MB
|
251 |
[ALLOC_TYPETREE_MAIN]
|
252 |
-
Peak usage frame count: [0-1.0 KB]:
|
253 |
Requested Block Size 2.0 MB
|
254 |
Peak Block count 1
|
255 |
Peak Allocated memory 1.0 KB
|
256 |
Peak Large allocation bytes 0 B
|
257 |
[ALLOC_TYPETREE_THREAD]
|
258 |
-
Peak usage frame count: [1.0 KB-2.0 KB]:
|
259 |
Requested Block Size 2.0 MB
|
260 |
Peak Block count 1
|
261 |
Peak Allocated memory 1.7 KB
|
|
|
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 0.087 seconds
|
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 |
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: 0.654828 ms
|
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.
|
|
|
53 |
[ALLOC_TEMP_TLS] TLS Allocator
|
54 |
StackAllocators :
|
55 |
[ALLOC_TEMP_MAIN]
|
56 |
+
Peak usage frame count: [8.0 KB-16.0 KB]: 1614 frames, [16.0 KB-32.0 KB]: 27 frames, [2.0 MB-4.0 MB]: 1 frames
|
57 |
Initial Block Size 4.0 MB
|
58 |
Current Block Size 4.0 MB
|
59 |
Peak Allocated Bytes 2.0 MB
|
|
|
169 |
Peak Allocated Bytes 0 B
|
170 |
Overflow Count 0
|
171 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
172 |
+
Peak main deferred allocation count 41
|
173 |
[ALLOC_BUCKET]
|
174 |
Large Block size 4.0 MB
|
175 |
Used Block count 1
|
176 |
Peak Allocated bytes 1.0 MB
|
177 |
[ALLOC_DEFAULT_MAIN]
|
178 |
+
Peak usage frame count: [4.0 MB-8.0 MB]: 1642 frames
|
179 |
Requested Block Size 16.0 MB
|
180 |
Peak Block count 1
|
181 |
+
Peak Allocated memory 6.2 MB
|
182 |
Peak Large allocation bytes 0 B
|
183 |
[ALLOC_DEFAULT_THREAD]
|
184 |
+
Peak usage frame count: [16.0 MB-32.0 MB]: 1642 frames
|
185 |
Requested Block Size 16.0 MB
|
186 |
Peak Block count 1
|
187 |
+
Peak Allocated memory 17.3 MB
|
188 |
Peak Large allocation bytes 16.0 MB
|
189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
190 |
Initial Block Size 2.0 MB
|
|
|
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]: 1144 frames, [64.0 KB-128.0 KB]: 498 frames
|
217 |
Requested Block Size 16.0 MB
|
218 |
Peak Block count 1
|
219 |
+
Peak Allocated memory 67.3 KB
|
220 |
Peak Large allocation bytes 0 B
|
221 |
[ALLOC_GFX_THREAD]
|
222 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 1642 frames
|
223 |
Requested Block Size 16.0 MB
|
224 |
Peak Block count 1
|
225 |
Peak Allocated memory 39.6 KB
|
|
|
231 |
Used Block count 1
|
232 |
Peak Allocated bytes 1.0 MB
|
233 |
[ALLOC_CACHEOBJECTS_MAIN]
|
234 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 1642 frames
|
235 |
Requested Block Size 4.0 MB
|
236 |
Peak Block count 1
|
237 |
Peak Allocated memory 0.6 MB
|
238 |
Peak Large allocation bytes 0 B
|
239 |
[ALLOC_CACHEOBJECTS_THREAD]
|
240 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 1641 frames, [2.0 MB-4.0 MB]: 1 frames
|
241 |
Requested Block Size 4.0 MB
|
242 |
Peak Block count 1
|
243 |
Peak Allocated memory 2.2 MB
|
|
|
249 |
Used Block count 1
|
250 |
Peak Allocated bytes 1.0 MB
|
251 |
[ALLOC_TYPETREE_MAIN]
|
252 |
+
Peak usage frame count: [0-1.0 KB]: 1642 frames
|
253 |
Requested Block Size 2.0 MB
|
254 |
Peak Block count 1
|
255 |
Peak Allocated memory 1.0 KB
|
256 |
Peak Large allocation bytes 0 B
|
257 |
[ALLOC_TYPETREE_THREAD]
|
258 |
+
Peak usage frame count: [1.0 KB-2.0 KB]: 1642 frames
|
259 |
Requested Block Size 2.0 MB
|
260 |
Peak Block count 1
|
261 |
Peak Allocated memory 1.7 KB
|
run_logs/timers.json
CHANGED
@@ -1,8 +1,154 @@
|
|
1 |
{
|
2 |
"name": "root",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"metadata": {
|
4 |
"timer_format_version": "0.1.0",
|
5 |
-
"start_time_seconds": "
|
6 |
"python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:04:59) [GCC 10.3.0]",
|
7 |
"command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
|
8 |
"mlagents_version": "0.31.0.dev0",
|
@@ -10,59 +156,59 @@
|
|
10 |
"communication_protocol_version": "1.5.0",
|
11 |
"pytorch_version": "1.11.0+cu102",
|
12 |
"numpy_version": "1.21.2",
|
13 |
-
"end_time_seconds": "
|
14 |
},
|
15 |
-
"total":
|
16 |
"count": 1,
|
17 |
-
"self": 0.
|
18 |
"children": {
|
19 |
"run_training.setup": {
|
20 |
-
"total": 0.
|
21 |
"count": 1,
|
22 |
-
"self": 0.
|
23 |
},
|
24 |
"TrainerController.start_learning": {
|
25 |
-
"total":
|
26 |
"count": 1,
|
27 |
-
"self": 0.
|
28 |
"children": {
|
29 |
"TrainerController._reset_env": {
|
30 |
-
"total": 3.
|
31 |
"count": 1,
|
32 |
-
"self": 3.
|
33 |
},
|
34 |
"TrainerController.advance": {
|
35 |
-
"total":
|
36 |
-
"count":
|
37 |
-
"self": 0.
|
38 |
"children": {
|
39 |
"env_step": {
|
40 |
-
"total":
|
41 |
-
"count":
|
42 |
-
"self":
|
43 |
"children": {
|
44 |
"SubprocessEnvManager._take_step": {
|
45 |
-
"total":
|
46 |
-
"count":
|
47 |
-
"self": 0.
|
48 |
"children": {
|
49 |
"TorchPolicy.evaluate": {
|
50 |
-
"total":
|
51 |
-
"count":
|
52 |
-
"self":
|
53 |
}
|
54 |
}
|
55 |
},
|
56 |
"workers": {
|
57 |
-
"total": 0.
|
58 |
-
"count":
|
59 |
"self": 0.0,
|
60 |
"children": {
|
61 |
"worker_root": {
|
62 |
-
"total":
|
63 |
-
"count":
|
64 |
"is_parallel": true,
|
65 |
-
"self":
|
66 |
"children": {
|
67 |
"run_training.setup": {
|
68 |
"total": 0.0,
|
@@ -71,48 +217,48 @@
|
|
71 |
"self": 0.0,
|
72 |
"children": {
|
73 |
"steps_from_proto": {
|
74 |
-
"total": 0.
|
75 |
"count": 1,
|
76 |
"is_parallel": true,
|
77 |
-
"self": 0.
|
78 |
"children": {
|
79 |
"_process_rank_one_or_two_observation": {
|
80 |
-
"total": 0.
|
81 |
"count": 10,
|
82 |
"is_parallel": true,
|
83 |
-
"self": 0.
|
84 |
}
|
85 |
}
|
86 |
},
|
87 |
"UnityEnvironment.step": {
|
88 |
-
"total": 0.
|
89 |
"count": 1,
|
90 |
"is_parallel": true,
|
91 |
-
"self": 0.
|
92 |
"children": {
|
93 |
"UnityEnvironment._generate_step_input": {
|
94 |
-
"total": 0.
|
95 |
"count": 1,
|
96 |
"is_parallel": true,
|
97 |
-
"self": 0.
|
98 |
},
|
99 |
"communicator.exchange": {
|
100 |
-
"total": 0.
|
101 |
"count": 1,
|
102 |
"is_parallel": true,
|
103 |
-
"self": 0.
|
104 |
},
|
105 |
"steps_from_proto": {
|
106 |
-
"total": 0.
|
107 |
"count": 1,
|
108 |
"is_parallel": true,
|
109 |
-
"self": 0.
|
110 |
"children": {
|
111 |
"_process_rank_one_or_two_observation": {
|
112 |
-
"total": 0.
|
113 |
"count": 10,
|
114 |
"is_parallel": true,
|
115 |
-
"self": 0.
|
116 |
}
|
117 |
}
|
118 |
}
|
@@ -121,34 +267,34 @@
|
|
121 |
}
|
122 |
},
|
123 |
"UnityEnvironment.step": {
|
124 |
-
"total":
|
125 |
-
"count":
|
126 |
"is_parallel": true,
|
127 |
-
"self":
|
128 |
"children": {
|
129 |
"UnityEnvironment._generate_step_input": {
|
130 |
-
"total":
|
131 |
-
"count":
|
132 |
"is_parallel": true,
|
133 |
-
"self":
|
134 |
},
|
135 |
"communicator.exchange": {
|
136 |
-
"total":
|
137 |
-
"count":
|
138 |
"is_parallel": true,
|
139 |
-
"self":
|
140 |
},
|
141 |
"steps_from_proto": {
|
142 |
-
"total":
|
143 |
-
"count":
|
144 |
"is_parallel": true,
|
145 |
-
"self":
|
146 |
"children": {
|
147 |
"_process_rank_one_or_two_observation": {
|
148 |
-
"total":
|
149 |
-
"count":
|
150 |
"is_parallel": true,
|
151 |
-
"self":
|
152 |
}
|
153 |
}
|
154 |
}
|
@@ -163,9 +309,9 @@
|
|
163 |
}
|
164 |
},
|
165 |
"trainer_threads": {
|
166 |
-
"total":
|
167 |
"count": 1,
|
168 |
-
"self":
|
169 |
"children": {
|
170 |
"thread_root": {
|
171 |
"total": 0.0,
|
@@ -174,16 +320,38 @@
|
|
174 |
"self": 0.0,
|
175 |
"children": {
|
176 |
"trainer_advance": {
|
177 |
-
"total":
|
178 |
-
"count":
|
179 |
"is_parallel": true,
|
180 |
-
"self":
|
181 |
"children": {
|
182 |
"process_trajectory": {
|
183 |
-
"total":
|
184 |
-
"count":
|
185 |
"is_parallel": true,
|
186 |
-
"self":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
187 |
}
|
188 |
}
|
189 |
}
|
@@ -192,14 +360,14 @@
|
|
192 |
}
|
193 |
},
|
194 |
"TrainerController._save_models": {
|
195 |
-
"total": 0.
|
196 |
"count": 1,
|
197 |
-
"self": 0.
|
198 |
"children": {
|
199 |
"RLTrainer._checkpoint": {
|
200 |
-
"total": 0.
|
201 |
"count": 1,
|
202 |
-
"self": 0.
|
203 |
}
|
204 |
}
|
205 |
}
|
|
|
1 |
{
|
2 |
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
+
"value": 2.2936456203460693,
|
6 |
+
"min": 2.2936456203460693,
|
7 |
+
"max": 2.866025924682617,
|
8 |
+
"count": 6
|
9 |
+
},
|
10 |
+
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
+
"value": 22152.029296875,
|
12 |
+
"min": 22152.029296875,
|
13 |
+
"max": 29350.97265625,
|
14 |
+
"count": 6
|
15 |
+
},
|
16 |
+
"SnowballTarget.Step.mean": {
|
17 |
+
"value": 59976.0,
|
18 |
+
"min": 9952.0,
|
19 |
+
"max": 59976.0,
|
20 |
+
"count": 6
|
21 |
+
},
|
22 |
+
"SnowballTarget.Step.sum": {
|
23 |
+
"value": 59976.0,
|
24 |
+
"min": 9952.0,
|
25 |
+
"max": 59976.0,
|
26 |
+
"count": 6
|
27 |
+
},
|
28 |
+
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 4.7627153396606445,
|
30 |
+
"min": 0.34516000747680664,
|
31 |
+
"max": 4.7627153396606445,
|
32 |
+
"count": 6
|
33 |
+
},
|
34 |
+
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 976.3566284179688,
|
36 |
+
"min": 66.96104431152344,
|
37 |
+
"max": 976.3566284179688,
|
38 |
+
"count": 6
|
39 |
+
},
|
40 |
+
"SnowballTarget.Environment.EpisodeLength.mean": {
|
41 |
+
"value": 199.0,
|
42 |
+
"min": 199.0,
|
43 |
+
"max": 199.0,
|
44 |
+
"count": 6
|
45 |
+
},
|
46 |
+
"SnowballTarget.Environment.EpisodeLength.sum": {
|
47 |
+
"value": 10945.0,
|
48 |
+
"min": 8756.0,
|
49 |
+
"max": 10945.0,
|
50 |
+
"count": 6
|
51 |
+
},
|
52 |
+
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.06690161215568272,
|
54 |
+
"min": 0.062435699654765905,
|
55 |
+
"max": 0.07468453972643485,
|
56 |
+
"count": 6
|
57 |
+
},
|
58 |
+
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.33450806077841355,
|
60 |
+
"min": 0.24974279861906362,
|
61 |
+
"max": 0.34266459971010643,
|
62 |
+
"count": 6
|
63 |
+
},
|
64 |
+
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.2576114994638106,
|
66 |
+
"min": 0.12173185954281293,
|
67 |
+
"max": 0.2876496722593027,
|
68 |
+
"count": 6
|
69 |
+
},
|
70 |
+
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
+
"value": 1.288057497319053,
|
72 |
+
"min": 0.4869274381712517,
|
73 |
+
"max": 1.3561888936103559,
|
74 |
+
"count": 6
|
75 |
+
},
|
76 |
+
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
+
"value": 2.544009152e-05,
|
78 |
+
"min": 2.544009152e-05,
|
79 |
+
"max": 0.00027294000901999997,
|
80 |
+
"count": 6
|
81 |
+
},
|
82 |
+
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
+
"value": 0.0001272004576,
|
84 |
+
"min": 0.0001272004576,
|
85 |
+
"max": 0.0011172001276,
|
86 |
+
"count": 6
|
87 |
+
},
|
88 |
+
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.10848000000000002,
|
90 |
+
"min": 0.10848000000000002,
|
91 |
+
"max": 0.19098,
|
92 |
+
"count": 6
|
93 |
+
},
|
94 |
+
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
+
"value": 0.5424000000000001,
|
96 |
+
"min": 0.49992000000000014,
|
97 |
+
"max": 0.8724000000000001,
|
98 |
+
"count": 6
|
99 |
+
},
|
100 |
+
"SnowballTarget.Policy.Beta.mean": {
|
101 |
+
"value": 0.0004331519999999999,
|
102 |
+
"min": 0.0004331519999999999,
|
103 |
+
"max": 0.004549902,
|
104 |
+
"count": 6
|
105 |
+
},
|
106 |
+
"SnowballTarget.Policy.Beta.sum": {
|
107 |
+
"value": 0.0021657599999999996,
|
108 |
+
"min": 0.0021657599999999996,
|
109 |
+
"max": 0.01863276,
|
110 |
+
"count": 6
|
111 |
+
},
|
112 |
+
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
+
"value": 11.345454545454546,
|
114 |
+
"min": 3.522727272727273,
|
115 |
+
"max": 11.345454545454546,
|
116 |
+
"count": 6
|
117 |
+
},
|
118 |
+
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
+
"value": 624.0,
|
120 |
+
"min": 155.0,
|
121 |
+
"max": 624.0,
|
122 |
+
"count": 6
|
123 |
+
},
|
124 |
+
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
+
"value": 11.345454545454546,
|
126 |
+
"min": 3.522727272727273,
|
127 |
+
"max": 11.345454545454546,
|
128 |
+
"count": 6
|
129 |
+
},
|
130 |
+
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
+
"value": 624.0,
|
132 |
+
"min": 155.0,
|
133 |
+
"max": 624.0,
|
134 |
+
"count": 6
|
135 |
+
},
|
136 |
+
"SnowballTarget.IsTraining.mean": {
|
137 |
+
"value": 1.0,
|
138 |
+
"min": 1.0,
|
139 |
+
"max": 1.0,
|
140 |
+
"count": 6
|
141 |
+
},
|
142 |
+
"SnowballTarget.IsTraining.sum": {
|
143 |
+
"value": 1.0,
|
144 |
+
"min": 1.0,
|
145 |
+
"max": 1.0,
|
146 |
+
"count": 6
|
147 |
+
}
|
148 |
+
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1680784928",
|
152 |
"python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:04:59) [GCC 10.3.0]",
|
153 |
"command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
|
154 |
"mlagents_version": "0.31.0.dev0",
|
|
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "1.11.0+cu102",
|
158 |
"numpy_version": "1.21.2",
|
159 |
+
"end_time_seconds": "1680785074"
|
160 |
},
|
161 |
+
"total": 145.45940288200018,
|
162 |
"count": 1,
|
163 |
+
"self": 0.48453295000035723,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.021707205999973667,
|
167 |
"count": 1,
|
168 |
+
"self": 0.021707205999973667
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 144.95316272599985,
|
172 |
"count": 1,
|
173 |
+
"self": 0.16149714400512494,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 3.113833035000198,
|
177 |
"count": 1,
|
178 |
+
"self": 3.113833035000198
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 141.46736615899476,
|
182 |
+
"count": 5471,
|
183 |
+
"self": 0.07663059798960603,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 141.39073556100516,
|
187 |
+
"count": 5471,
|
188 |
+
"self": 101.17150663101233,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 40.136498686992354,
|
192 |
+
"count": 5471,
|
193 |
+
"self": 0.5052758879951398,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 39.631222798997214,
|
197 |
+
"count": 5471,
|
198 |
+
"self": 39.631222798997214
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
+
"total": 0.08273024300046927,
|
204 |
+
"count": 5471,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
+
"total": 144.3440517189972,
|
209 |
+
"count": 5471,
|
210 |
"is_parallel": true,
|
211 |
+
"self": 65.2818101589994,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
+
"total": 0.001980684000045585,
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
+
"self": 0.0006041300000561023,
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
+
"total": 0.0013765539999894827,
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
+
"self": 0.0013765539999894827
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
+
"total": 0.08273509900004683,
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.0005849889998899016,
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
+
"total": 0.0003496950000680954,
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
+
"self": 0.0003496950000680954
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
+
"total": 0.07961141800001315,
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.07961141800001315
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
+
"total": 0.0021889970000756875,
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.00044234500091988593,
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
+
"total": 0.0017466519991558016,
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 0.0017466519991558016
|
262 |
}
|
263 |
}
|
264 |
}
|
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
+
"total": 79.0622415599978,
|
271 |
+
"count": 5470,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 2.8316271569817673,
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
+
"total": 1.7115460930017434,
|
277 |
+
"count": 5470,
|
278 |
"is_parallel": true,
|
279 |
+
"self": 1.7115460930017434
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
+
"total": 64.90729787000214,
|
283 |
+
"count": 5470,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 64.90729787000214
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
+
"total": 9.611770440012151,
|
289 |
+
"count": 5470,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 1.9485815850021027,
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
+
"total": 7.663188855010048,
|
295 |
+
"count": 54700,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 7.663188855010048
|
298 |
}
|
299 |
}
|
300 |
}
|
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
+
"total": 0.0001451719999749912,
|
313 |
"count": 1,
|
314 |
+
"self": 0.0001451719999749912,
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
+
"total": 140.48691986093695,
|
324 |
+
"count": 114276,
|
325 |
"is_parallel": true,
|
326 |
+
"self": 2.6478413979371,
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
+
"total": 78.75249613300025,
|
330 |
+
"count": 114276,
|
331 |
"is_parallel": true,
|
332 |
+
"self": 78.52266481600032,
|
333 |
+
"children": {
|
334 |
+
"RLTrainer._checkpoint": {
|
335 |
+
"total": 0.22983131699993464,
|
336 |
+
"count": 1,
|
337 |
+
"is_parallel": true,
|
338 |
+
"self": 0.22983131699993464
|
339 |
+
}
|
340 |
+
}
|
341 |
+
},
|
342 |
+
"_update_policy": {
|
343 |
+
"total": 59.0865823299996,
|
344 |
+
"count": 27,
|
345 |
+
"is_parallel": true,
|
346 |
+
"self": 16.2498989529995,
|
347 |
+
"children": {
|
348 |
+
"TorchPPOOptimizer.update": {
|
349 |
+
"total": 42.8366833770001,
|
350 |
+
"count": 1374,
|
351 |
+
"is_parallel": true,
|
352 |
+
"self": 42.8366833770001
|
353 |
+
}
|
354 |
+
}
|
355 |
}
|
356 |
}
|
357 |
}
|
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
+
"total": 0.21032121599978382,
|
364 |
"count": 1,
|
365 |
+
"self": 0.0012572019998060568,
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
+
"total": 0.20906401399997776,
|
369 |
"count": 1,
|
370 |
+
"self": 0.20906401399997776
|
371 |
}
|
372 |
}
|
373 |
}
|
run_logs/training_status.json
CHANGED
@@ -2,22 +2,31 @@
|
|
2 |
"SnowballTarget": {
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
-
"steps":
|
6 |
-
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-
|
7 |
-
"reward":
|
8 |
-
"creation_time":
|
9 |
"auxillary_file_paths": [
|
10 |
-
"results/SnowballTarget1/SnowballTarget/SnowballTarget-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
]
|
12 |
}
|
13 |
],
|
14 |
"final_checkpoint": {
|
15 |
-
"steps":
|
16 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
17 |
-
"reward":
|
18 |
-
"creation_time":
|
19 |
"auxillary_file_paths": [
|
20 |
-
"results/SnowballTarget1/SnowballTarget/SnowballTarget-
|
21 |
]
|
22 |
}
|
23 |
},
|
|
|
2 |
"SnowballTarget": {
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
+
"steps": 49936,
|
6 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
|
7 |
+
"reward": 10.818181818181818,
|
8 |
+
"creation_time": 1680785050.0995784,
|
9 |
"auxillary_file_paths": [
|
10 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
|
11 |
+
]
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"steps": 60104,
|
15 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.onnx",
|
16 |
+
"reward": 12.454545454545455,
|
17 |
+
"creation_time": 1680785073.8293626,
|
18 |
+
"auxillary_file_paths": [
|
19 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.pt"
|
20 |
]
|
21 |
}
|
22 |
],
|
23 |
"final_checkpoint": {
|
24 |
+
"steps": 60104,
|
25 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
26 |
+
"reward": 12.454545454545455,
|
27 |
+
"creation_time": 1680785073.8293626,
|
28 |
"auxillary_file_paths": [
|
29 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.pt"
|
30 |
]
|
31 |
}
|
32 |
},
|