First Push
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/SnowballTarget-249984.onnx +3 -0
- SnowballTarget/SnowballTarget-249984.pt +3 -0
- SnowballTarget/SnowballTarget-279224.onnx +3 -0
- SnowballTarget/SnowballTarget-279224.pt +3 -0
- SnowballTarget/checkpoint.pt +1 -1
- SnowballTarget/events.out.tfevents.1696418835.c21b34188a69.10739.0 +3 -0
- config.json +1 -1
- configuration.yaml +2 -2
- run_logs/Player-0.log +17 -18
- run_logs/timers.json +162 -162
- run_logs/training_status.json +22 -4
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 sha256:3ff58e567f26b0ff8304c3908047d11baea26d70e758e1fb01f691a175afc3d0
|
3 |
size 646532
|
SnowballTarget/SnowballTarget-249984.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4762accd0802ded289bf8e5a80a8af14b81fe389d792ca37a2728282bf7f6039
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-249984.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:111de03a05f8e3d1b0262a1f8ff27b83b9ace9d19f00d2d505b40c5f74ea6833
|
3 |
+
size 3843968
|
SnowballTarget/SnowballTarget-279224.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ff58e567f26b0ff8304c3908047d11baea26d70e758e1fb01f691a175afc3d0
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-279224.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7479627a0eaf3b6c745b518b94b4c89069577ec273705801364499ea9113805e
|
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 3843968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7479627a0eaf3b6c745b518b94b4c89069577ec273705801364499ea9113805e
|
3 |
size 3843968
|
SnowballTarget/events.out.tfevents.1696418835.c21b34188a69.10739.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a493905dba7e4eaa56b6f2ccc0427e8f857d10dec5b30800e68d69d1799019d
|
3 |
+
size 6868
|
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": 500000, "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": true, "force": false, "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
|
@@ -67,7 +67,7 @@ checkpoint_settings:
|
|
67 |
run_id: SnowballTarget1
|
68 |
initialize_from: null
|
69 |
load_model: false
|
70 |
-
resume:
|
71 |
force: false
|
72 |
train_model: false
|
73 |
inference: false
|
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
+
max_steps: 500000
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
|
|
67 |
run_id: SnowballTarget1
|
68 |
initialize_from: null
|
69 |
load_model: false
|
70 |
+
resume: true
|
71 |
force: false
|
72 |
train_model: false
|
73 |
inference: 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)
|
@@ -45,15 +42,17 @@ 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.
|
|
|
|
|
52 |
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 +168,22 @@ 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 6.
|
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 +212,13 @@ 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 67.
|
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 +230,13 @@ 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 +248,13 @@ 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
|
|
|
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 0.085 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: 0.660902 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.
|
49 |
+
abort_threads: Failed aborting id: 0x7a64190ba640, mono_thread_manage will ignore it
|
50 |
+
|
51 |
Memory Statistics:
|
52 |
[ALLOC_TEMP_TLS] TLS Allocator
|
53 |
StackAllocators :
|
54 |
[ALLOC_TEMP_MAIN]
|
55 |
+
Peak usage frame count: [8.0 KB-16.0 KB]: 2143 frames, [16.0 KB-32.0 KB]: 36 frames, [2.0 MB-4.0 MB]: 1 frames
|
56 |
Initial Block Size 4.0 MB
|
57 |
Current Block Size 4.0 MB
|
58 |
Peak Allocated Bytes 2.0 MB
|
|
|
168 |
Peak Allocated Bytes 0 B
|
169 |
Overflow Count 0
|
170 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
171 |
+
Peak main deferred allocation count 41
|
172 |
[ALLOC_BUCKET]
|
173 |
Large Block size 4.0 MB
|
174 |
Used Block count 1
|
175 |
Peak Allocated bytes 1.0 MB
|
176 |
[ALLOC_DEFAULT_MAIN]
|
177 |
+
Peak usage frame count: [4.0 MB-8.0 MB]: 2180 frames
|
178 |
Requested Block Size 16.0 MB
|
179 |
Peak Block count 1
|
180 |
+
Peak Allocated memory 6.4 MB
|
181 |
Peak Large allocation bytes 0 B
|
182 |
[ALLOC_DEFAULT_THREAD]
|
183 |
+
Peak usage frame count: [16.0 MB-32.0 MB]: 2180 frames
|
184 |
Requested Block Size 16.0 MB
|
185 |
Peak Block count 1
|
186 |
+
Peak Allocated memory 17.3 MB
|
187 |
Peak Large allocation bytes 16.0 MB
|
188 |
[ALLOC_TEMP_JOB_1_FRAME]
|
189 |
Initial Block Size 2.0 MB
|
|
|
212 |
Used Block count 1
|
213 |
Peak Allocated bytes 1.0 MB
|
214 |
[ALLOC_GFX_MAIN]
|
215 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 2050 frames, [64.0 KB-128.0 KB]: 130 frames
|
216 |
Requested Block Size 16.0 MB
|
217 |
Peak Block count 1
|
218 |
+
Peak Allocated memory 67.2 KB
|
219 |
Peak Large allocation bytes 0 B
|
220 |
[ALLOC_GFX_THREAD]
|
221 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 2180 frames
|
222 |
Requested Block Size 16.0 MB
|
223 |
Peak Block count 1
|
224 |
Peak Allocated memory 39.6 KB
|
|
|
230 |
Used Block count 1
|
231 |
Peak Allocated bytes 1.0 MB
|
232 |
[ALLOC_CACHEOBJECTS_MAIN]
|
233 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 2180 frames
|
234 |
Requested Block Size 4.0 MB
|
235 |
Peak Block count 1
|
236 |
Peak Allocated memory 0.6 MB
|
237 |
Peak Large allocation bytes 0 B
|
238 |
[ALLOC_CACHEOBJECTS_THREAD]
|
239 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 2179 frames, [2.0 MB-4.0 MB]: 1 frames
|
240 |
Requested Block Size 4.0 MB
|
241 |
Peak Block count 1
|
242 |
Peak Allocated memory 2.2 MB
|
|
|
248 |
Used Block count 1
|
249 |
Peak Allocated bytes 1.0 MB
|
250 |
[ALLOC_TYPETREE_MAIN]
|
251 |
+
Peak usage frame count: [0-1.0 KB]: 2180 frames
|
252 |
Requested Block Size 2.0 MB
|
253 |
Peak Block count 1
|
254 |
Peak Allocated memory 1.0 KB
|
255 |
Peak Large allocation bytes 0 B
|
256 |
[ALLOC_TYPETREE_THREAD]
|
257 |
+
Peak usage frame count: [1.0 KB-2.0 KB]: 2180 frames
|
258 |
Requested Block Size 2.0 MB
|
259 |
Peak Block count 1
|
260 |
Peak Allocated memory 1.7 KB
|
run_logs/timers.json
CHANGED
@@ -2,213 +2,213 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
-
"value":
|
6 |
-
"min":
|
7 |
-
"max":
|
8 |
-
"count":
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
-
"count":
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
-
"value":
|
18 |
-
"min":
|
19 |
-
"max":
|
20 |
-
"count":
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
-
"value":
|
24 |
-
"min":
|
25 |
-
"max":
|
26 |
-
"count":
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
-
"value":
|
30 |
-
"min":
|
31 |
-
"max":
|
32 |
-
"count":
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
-
"count":
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
41 |
"value": 199.0,
|
42 |
"min": 199.0,
|
43 |
"max": 199.0,
|
44 |
-
"count":
|
45 |
},
|
46 |
"SnowballTarget.Environment.EpisodeLength.sum": {
|
47 |
"value": 8756.0,
|
48 |
"min": 8756.0,
|
49 |
"max": 10945.0,
|
50 |
-
"count":
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
-
"value": 0.
|
54 |
-
"min": 0.
|
55 |
-
"max": 0.
|
56 |
-
"count":
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
-
"value": 0.
|
60 |
-
"min": 0.
|
61 |
-
"max": 0.
|
62 |
-
"count":
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
-
"value": 0.
|
66 |
-
"min": 0.
|
67 |
-
"max": 0.
|
68 |
-
"count":
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
-
"value": 0.
|
72 |
-
"min": 0.
|
73 |
-
"max":
|
74 |
-
"count":
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
-
"value":
|
78 |
-
"min":
|
79 |
-
"max": 0.
|
80 |
-
"count":
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
-
"value":
|
84 |
-
"min":
|
85 |
-
"max": 0.
|
86 |
-
"count":
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": 0.
|
91 |
-
"max": 0.
|
92 |
-
"count":
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
-
"value": 0.
|
96 |
-
"min": 0.
|
97 |
-
"max": 0.
|
98 |
-
"count":
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
-
"value": 0.
|
102 |
-
"min": 0.
|
103 |
-
"max": 0.
|
104 |
-
"count":
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
-
"value": 0.
|
108 |
-
"min": 0.
|
109 |
-
"max": 0.
|
110 |
-
"count":
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
-
"value":
|
114 |
-
"min":
|
115 |
-
"max":
|
116 |
-
"count":
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
-
"value":
|
120 |
-
"min":
|
121 |
-
"max":
|
122 |
-
"count":
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
-
"value":
|
126 |
-
"min":
|
127 |
-
"max":
|
128 |
-
"count":
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
-
"value":
|
132 |
-
"min":
|
133 |
-
"max":
|
134 |
-
"count":
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
-
"count":
|
141 |
},
|
142 |
"SnowballTarget.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
-
"count":
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
-
"start_time_seconds": "
|
152 |
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
|
153 |
-
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
|
154 |
"mlagents_version": "0.31.0.dev0",
|
155 |
"mlagents_envs_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": "
|
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":
|
183 |
-
"self": 0.
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
-
"total":
|
187 |
-
"count":
|
188 |
-
"self":
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
-
"total":
|
192 |
-
"count":
|
193 |
-
"self":
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
-
"total":
|
197 |
-
"count":
|
198 |
-
"self":
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
-
"total": 0.
|
204 |
-
"count":
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
-
"total":
|
209 |
-
"count":
|
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":
|
272 |
"is_parallel": true,
|
273 |
-
"self":
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
-
"total":
|
277 |
-
"count":
|
278 |
"is_parallel": true,
|
279 |
-
"self":
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
-
"total":
|
283 |
-
"count":
|
284 |
"is_parallel": true,
|
285 |
-
"self":
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
-
"total":
|
289 |
-
"count":
|
290 |
"is_parallel": true,
|
291 |
-
"self":
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
-
"total":
|
295 |
-
"count":
|
296 |
"is_parallel": true,
|
297 |
-
"self":
|
298 |
}
|
299 |
}
|
300 |
}
|
@@ -309,9 +309,9 @@
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
-
"total": 0.
|
313 |
"count": 1,
|
314 |
-
"self": 0.
|
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":
|
336 |
-
"count":
|
337 |
"is_parallel": true,
|
338 |
-
"self":
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
-
"total":
|
344 |
-
"count":
|
345 |
"is_parallel": true,
|
346 |
-
"self":
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
-
"total":
|
350 |
-
"count":
|
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": 0.9509430527687073,
|
6 |
+
"min": 0.9332674741744995,
|
7 |
+
"max": 1.0425547361373901,
|
8 |
+
"count": 7
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
+
"value": 9675.845703125,
|
12 |
+
"min": 8900.787109375,
|
13 |
+
"max": 10665.3349609375,
|
14 |
+
"count": 7
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
+
"value": 269976.0,
|
18 |
+
"min": 209936.0,
|
19 |
+
"max": 269976.0,
|
20 |
+
"count": 7
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
+
"value": 269976.0,
|
24 |
+
"min": 209936.0,
|
25 |
+
"max": 269976.0,
|
26 |
+
"count": 7
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 13.233717918395996,
|
30 |
+
"min": 12.270806312561035,
|
31 |
+
"max": 13.233717918395996,
|
32 |
+
"count": 7
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 2580.574951171875,
|
36 |
+
"min": 2355.994873046875,
|
37 |
+
"max": 2664.337890625,
|
38 |
+
"count": 7
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
41 |
"value": 199.0,
|
42 |
"min": 199.0,
|
43 |
"max": 199.0,
|
44 |
+
"count": 7
|
45 |
},
|
46 |
"SnowballTarget.Environment.EpisodeLength.sum": {
|
47 |
"value": 8756.0,
|
48 |
"min": 8756.0,
|
49 |
"max": 10945.0,
|
50 |
+
"count": 7
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.06434979716241108,
|
54 |
+
"min": 0.06434979716241108,
|
55 |
+
"max": 0.07744694704314872,
|
56 |
+
"count": 7
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.25739918864964434,
|
60 |
+
"min": 0.25739918864964434,
|
61 |
+
"max": 0.3872347352157436,
|
62 |
+
"count": 7
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.17866915223353047,
|
66 |
+
"min": 0.17456258690970783,
|
67 |
+
"max": 0.19856594356836058,
|
68 |
+
"count": 7
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
+
"value": 0.7146766089341219,
|
72 |
+
"min": 0.6982503476388313,
|
73 |
+
"max": 0.9928297178418029,
|
74 |
+
"count": 7
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
+
"value": 0.00014104565298479998,
|
78 |
+
"min": 0.00014104565298479998,
|
79 |
+
"max": 0.00017668564110480002,
|
80 |
+
"count": 7
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
+
"value": 0.0005641826119391999,
|
84 |
+
"min": 0.0005641826119391999,
|
85 |
+
"max": 0.000853728215424,
|
86 |
+
"count": 7
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.1470152,
|
90 |
+
"min": 0.1470152,
|
91 |
+
"max": 0.15889520000000001,
|
92 |
+
"count": 7
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
+
"value": 0.5880608,
|
96 |
+
"min": 0.5880608,
|
97 |
+
"max": 0.7845760000000002,
|
98 |
+
"count": 7
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
+
"value": 0.00235605848,
|
102 |
+
"min": 0.00235605848,
|
103 |
+
"max": 0.002948870480000001,
|
104 |
+
"count": 7
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
+
"value": 0.00942423392,
|
108 |
+
"min": 0.00942423392,
|
109 |
+
"max": 0.0142503424,
|
110 |
+
"count": 7
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
+
"value": 25.954545454545453,
|
114 |
+
"min": 23.818181818181817,
|
115 |
+
"max": 25.954545454545453,
|
116 |
+
"count": 7
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
+
"value": 1142.0,
|
120 |
+
"min": 1048.0,
|
121 |
+
"max": 1411.0,
|
122 |
+
"count": 7
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
+
"value": 25.954545454545453,
|
126 |
+
"min": 23.818181818181817,
|
127 |
+
"max": 25.954545454545453,
|
128 |
+
"count": 7
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
+
"value": 1142.0,
|
132 |
+
"min": 1048.0,
|
133 |
+
"max": 1411.0,
|
134 |
+
"count": 7
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
+
"count": 7
|
141 |
},
|
142 |
"SnowballTarget.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
+
"count": 7
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1696418834",
|
152 |
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
|
153 |
+
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo.yaml --resume --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
|
154 |
"mlagents_version": "0.31.0.dev0",
|
155 |
"mlagents_envs_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": "1696419045"
|
160 |
},
|
161 |
+
"total": 211.43181110000023,
|
162 |
"count": 1,
|
163 |
+
"self": 0.008607448000020668,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.04204078000020672,
|
167 |
"count": 1,
|
168 |
+
"self": 0.04204078000020672
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 211.381162872,
|
172 |
"count": 1,
|
173 |
+
"self": 0.8524889690129385,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 4.148062613000093,
|
177 |
"count": 1,
|
178 |
+
"self": 4.148062613000093
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 206.06741542598684,
|
182 |
+
"count": 7264,
|
183 |
+
"self": 0.12974490201804656,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 205.9376705239688,
|
187 |
+
"count": 7264,
|
188 |
+
"self": 150.14040884797123,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 55.66749211900424,
|
192 |
+
"count": 7264,
|
193 |
+
"self": 0.7677587529815355,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 54.8997333660227,
|
197 |
+
"count": 7264,
|
198 |
+
"self": 54.8997333660227
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
+
"total": 0.12976955699332393,
|
204 |
+
"count": 7264,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
+
"total": 209.2923571470028,
|
209 |
+
"count": 7264,
|
210 |
"is_parallel": true,
|
211 |
+
"self": 99.49096950098556,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
+
"total": 0.002168768000046839,
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
+
"self": 0.0006789990002289414,
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
+
"total": 0.0014897689998178976,
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
+
"self": 0.0014897689998178976
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
+
"total": 0.07897069000000556,
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.0006831480000073498,
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
+
"total": 0.0005036219999965397,
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
+
"self": 0.0005036219999965397
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
+
"total": 0.07441088099994886,
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.07441088099994886
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
+
"total": 0.003373039000052813,
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.0013687670007129782,
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
+
"total": 0.002004271999339835,
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 0.002004271999339835
|
262 |
}
|
263 |
}
|
264 |
}
|
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
+
"total": 109.80138764601725,
|
271 |
+
"count": 7263,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 4.500908722024633,
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
+
"total": 2.3794146300078864,
|
277 |
+
"count": 7263,
|
278 |
"is_parallel": true,
|
279 |
+
"self": 2.3794146300078864
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
+
"total": 86.55531314499422,
|
283 |
+
"count": 7263,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 86.55531314499422
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
+
"total": 16.365751148990512,
|
289 |
+
"count": 7263,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 3.015981797954737,
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
+
"total": 13.349769351035775,
|
295 |
+
"count": 72630,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 13.349769351035775
|
298 |
}
|
299 |
}
|
300 |
}
|
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
+
"total": 0.001425604000360181,
|
313 |
"count": 1,
|
314 |
+
"self": 0.001425604000360181,
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
+
"total": 204.96596370299812,
|
324 |
+
"count": 194646,
|
325 |
"is_parallel": true,
|
326 |
+
"self": 4.581322357907993,
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
+
"total": 112.13210191809003,
|
330 |
+
"count": 194646,
|
331 |
"is_parallel": true,
|
332 |
+
"self": 111.92670309709001,
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
+
"total": 0.20539882100001705,
|
336 |
+
"count": 1,
|
337 |
"is_parallel": true,
|
338 |
+
"self": 0.20539882100001705
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
+
"total": 88.2525394270001,
|
344 |
+
"count": 36,
|
345 |
"is_parallel": true,
|
346 |
+
"self": 35.320939524002824,
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
+
"total": 52.93159990299728,
|
350 |
+
"count": 1833,
|
351 |
"is_parallel": true,
|
352 |
+
"self": 52.93159990299728
|
353 |
}
|
354 |
}
|
355 |
}
|
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
+
"total": 0.3117702599997756,
|
364 |
"count": 1,
|
365 |
+
"self": 0.0019030459998248261,
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
+
"total": 0.30986721399995076,
|
369 |
"count": 1,
|
370 |
+
"self": 0.30986721399995076
|
371 |
}
|
372 |
}
|
373 |
}
|
run_logs/training_status.json
CHANGED
@@ -45,15 +45,33 @@
|
|
45 |
"auxillary_file_paths": [
|
46 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
-
"steps":
|
52 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
53 |
-
"reward":
|
54 |
-
"creation_time":
|
55 |
"auxillary_file_paths": [
|
56 |
-
"results/SnowballTarget1/SnowballTarget/SnowballTarget-
|
57 |
]
|
58 |
}
|
59 |
},
|
|
|
45 |
"auxillary_file_paths": [
|
46 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
]
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"steps": 249984,
|
51 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
|
52 |
+
"reward": 26.181818181818183,
|
53 |
+
"creation_time": 1696418968.667711,
|
54 |
+
"auxillary_file_paths": [
|
55 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
|
56 |
+
]
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"steps": 279224,
|
60 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.onnx",
|
61 |
+
"reward": null,
|
62 |
+
"creation_time": 1696419045.9717553,
|
63 |
+
"auxillary_file_paths": [
|
64 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.pt"
|
65 |
+
]
|
66 |
}
|
67 |
],
|
68 |
"final_checkpoint": {
|
69 |
+
"steps": 279224,
|
70 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
71 |
+
"reward": null,
|
72 |
+
"creation_time": 1696419045.9717553,
|
73 |
"auxillary_file_paths": [
|
74 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-279224.pt"
|
75 |
]
|
76 |
}
|
77 |
},
|