First Push
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/SnowballTarget-149984.onnx +1 -1
- SnowballTarget/SnowballTarget-149984.pt +1 -1
- SnowballTarget/SnowballTarget-199984.onnx +1 -1
- SnowballTarget/SnowballTarget-199984.pt +1 -1
- SnowballTarget/SnowballTarget-200112.onnx +1 -1
- SnowballTarget/SnowballTarget-200112.pt +1 -1
- SnowballTarget/SnowballTarget-49936.onnx +1 -1
- SnowballTarget/SnowballTarget-49936.pt +1 -1
- SnowballTarget/SnowballTarget-99960.onnx +1 -1
- SnowballTarget/SnowballTarget-99960.pt +1 -1
- SnowballTarget/checkpoint.pt +1 -1
- SnowballTarget/{events.out.tfevents.1682810743.0bc13333712c.2979.0 → events.out.tfevents.1682812051.0bc13333712c.8883.0} +2 -2
- config.json +1 -1
- configuration.yaml +4 -4
- run_logs/Player-0.log +7 -10
- run_logs/timers.json +117 -117
- 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 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d067be517abfd0a866b519c8a10e75528ffc697f902d34ff0cae38a0dcaad0d3
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-149984.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:b578c97c9abaea415a9faad2f42e95b14a6e3ac566fe3b30cc763d9be50be98a
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-149984.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:a7e5ca724d345e69d3288866192e1fe6968e2e545d9c707e122e3907233ba9ab
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-199984.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:d067be517abfd0a866b519c8a10e75528ffc697f902d34ff0cae38a0dcaad0d3
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-199984.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:bcc0b9af53d5a559b27153e7da91225c63645dbbc35a101001a5abf744eb30e9
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-200112.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:d067be517abfd0a866b519c8a10e75528ffc697f902d34ff0cae38a0dcaad0d3
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-200112.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 sha256:4785622246a7878127cf07e15500994255f11aaad2be3cfb6ac2882de6e491a7
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-49936.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 sha256:2025485c4df6fefb01b863f84953e3452f74162ff64a3b9e176a29e6064bc915
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-49936.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 sha256:0882f7fd846b348b4162048fe008a75451fc9097e7162ddc96648f6affeafb12
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-99960.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 sha256:4eaa1c4a767f8fa18a6ddfcf9ccdda2c530f6c3f23c8b89f5d14503c758fbb7f
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-99960.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 sha256:225c1512cf0b480553eced4b7d15bedee225b56af37dce0370d9c8baaa58f0eb
|
| 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 sha256:4785622246a7878127cf07e15500994255f11aaad2be3cfb6ac2882de6e491a7
|
| 3 |
size 3843968
|
SnowballTarget/{events.out.tfevents.1682810743.0bc13333712c.2979.0 → events.out.tfevents.1682812051.0bc13333712c.8883.0}
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:b5446a921191025be77bdc55804e482eb8d42d8f3ad968538c3d61f4f33927f7
|
| 3 |
+
size 23380
|
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": 0.2, "lambd": 0.94, "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": 0.98, "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, "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": "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
|
@@ -5,10 +5,10 @@ behaviors:
|
|
| 5 |
hyperparameters:
|
| 6 |
batch_size: 128
|
| 7 |
buffer_size: 2048
|
| 8 |
-
learning_rate: 0.
|
| 9 |
beta: 0.005
|
| 10 |
epsilon: 0.2
|
| 11 |
-
lambd: 0.
|
| 12 |
num_epoch: 3
|
| 13 |
shared_critic: false
|
| 14 |
learning_rate_schedule: linear
|
|
@@ -25,7 +25,7 @@ behaviors:
|
|
| 25 |
deterministic: false
|
| 26 |
reward_signals:
|
| 27 |
extrinsic:
|
| 28 |
-
gamma: 0.
|
| 29 |
strength: 1.0
|
| 30 |
network_settings:
|
| 31 |
normalize: false
|
|
@@ -64,7 +64,7 @@ engine_settings:
|
|
| 64 |
no_graphics: true
|
| 65 |
environment_parameters: null
|
| 66 |
checkpoint_settings:
|
| 67 |
-
run_id:
|
| 68 |
initialize_from: null
|
| 69 |
load_model: false
|
| 70 |
resume: false
|
|
|
|
| 5 |
hyperparameters:
|
| 6 |
batch_size: 128
|
| 7 |
buffer_size: 2048
|
| 8 |
+
learning_rate: 0.0006
|
| 9 |
beta: 0.005
|
| 10 |
epsilon: 0.2
|
| 11 |
+
lambd: 0.94
|
| 12 |
num_epoch: 3
|
| 13 |
shared_critic: false
|
| 14 |
learning_rate_schedule: linear
|
|
|
|
| 25 |
deterministic: false
|
| 26 |
reward_signals:
|
| 27 |
extrinsic:
|
| 28 |
+
gamma: 0.98
|
| 29 |
strength: 1.0
|
| 30 |
network_settings:
|
| 31 |
normalize: false
|
|
|
|
| 64 |
no_graphics: true
|
| 65 |
environment_parameters: null
|
| 66 |
checkpoint_settings:
|
| 67 |
+
run_id: SnowballTarget2
|
| 68 |
initialize_from: null
|
| 69 |
load_model: false
|
| 70 |
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: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 +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:
|
| 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
|
|
@@ -178,13 +175,13 @@ Memory Statistics:
|
|
| 178 |
Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
|
| 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]: 5461 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
|
|
@@ -213,10 +210,10 @@ 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]: 5461 frames
|
|
|
|
| 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 0.082 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: 0.667944 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 41
|
| 170 |
[ALLOC_BUCKET]
|
| 171 |
Large Block size 4.0 MB
|
| 172 |
Used Block count 1
|
|
|
|
| 175 |
Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
|
| 176 |
Requested Block Size 16.0 MB
|
| 177 |
Peak Block count 1
|
| 178 |
+
Peak Allocated memory 6.8 MB
|
| 179 |
Peak Large allocation bytes 0 B
|
| 180 |
[ALLOC_DEFAULT_THREAD]
|
| 181 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
|
| 182 |
Requested Block Size 16.0 MB
|
| 183 |
Peak Block count 1
|
| 184 |
+
Peak Allocated memory 17.8 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]: 4285 frames, [64.0 KB-128.0 KB]: 1176 frames
|
| 214 |
Requested Block Size 16.0 MB
|
| 215 |
Peak Block count 1
|
| 216 |
+
Peak Allocated memory 67.3 KB
|
| 217 |
Peak Large allocation bytes 0 B
|
| 218 |
[ALLOC_GFX_THREAD]
|
| 219 |
Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
|
run_logs/timers.json
CHANGED
|
@@ -2,15 +2,15 @@
|
|
| 2 |
"name": "root",
|
| 3 |
"gauges": {
|
| 4 |
"SnowballTarget.Policy.Entropy.mean": {
|
| 5 |
-
"value": 0.
|
| 6 |
-
"min": 0.
|
| 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": {
|
|
@@ -50,39 +50,39 @@
|
|
| 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": {
|
|
@@ -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": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
|
| 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": "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": 457.
|
| 187 |
-
"count":
|
| 188 |
-
"self":
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
-
"total":
|
| 192 |
-
"count":
|
| 193 |
-
"self": 1.
|
| 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": 5.
|
| 277 |
-
"count":
|
| 278 |
"is_parallel": true,
|
| 279 |
-
"self": 5.
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
-
"total": 196.
|
| 283 |
-
"count":
|
| 284 |
"is_parallel": true,
|
| 285 |
-
"self": 196.
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
-
"total": 31.
|
| 289 |
-
"count":
|
| 290 |
"is_parallel": true,
|
| 291 |
-
"self": 6.
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
-
"total": 25.
|
| 295 |
-
"count":
|
| 296 |
"is_parallel": true,
|
| 297 |
-
"self": 25.
|
| 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": 454.
|
| 324 |
-
"count":
|
| 325 |
"is_parallel": true,
|
| 326 |
-
"self": 9.
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
-
"total": 248.
|
| 330 |
-
"count":
|
| 331 |
"is_parallel": true,
|
| 332 |
-
"self": 247.
|
| 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": 196.
|
| 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": 0.8168727159500122,
|
| 6 |
+
"min": 0.8056074976921082,
|
| 7 |
+
"max": 2.84737491607666,
|
| 8 |
"count": 20
|
| 9 |
},
|
| 10 |
"SnowballTarget.Policy.Entropy.sum": {
|
| 11 |
+
"value": 7799.50048828125,
|
| 12 |
+
"min": 7799.50048828125,
|
| 13 |
+
"max": 29159.966796875,
|
| 14 |
"count": 20
|
| 15 |
},
|
| 16 |
"SnowballTarget.Step.mean": {
|
|
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
+
"value": 6.714617729187012,
|
| 30 |
+
"min": 0.2590954601764679,
|
| 31 |
+
"max": 6.714617729187012,
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
+
"value": 1309.3504638671875,
|
| 36 |
+
"min": 50.26451873779297,
|
| 37 |
+
"max": 1361.91845703125,
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
|
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 53 |
+
"value": 0.0698590681229903,
|
| 54 |
+
"min": 0.06157629102669364,
|
| 55 |
+
"max": 0.07728244612271916,
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 59 |
+
"value": 0.2794362724919612,
|
| 60 |
+
"min": 0.2672292279178281,
|
| 61 |
+
"max": 0.36412036234761735,
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 65 |
+
"value": 0.14618440377799904,
|
| 66 |
+
"min": 0.09518700041557096,
|
| 67 |
+
"max": 0.20158036637539958,
|
| 68 |
"count": 20
|
| 69 |
},
|
| 70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 71 |
+
"value": 0.5847376151119962,
|
| 72 |
+
"min": 0.38074800166228384,
|
| 73 |
+
"max": 1.007901831876998,
|
| 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": {
|
|
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
+
"value": 26.068181818181817,
|
| 114 |
+
"min": 3.477272727272727,
|
| 115 |
+
"max": 26.454545454545453,
|
| 116 |
"count": 20
|
| 117 |
},
|
| 118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
| 119 |
+
"value": 1147.0,
|
| 120 |
+
"min": 153.0,
|
| 121 |
+
"max": 1455.0,
|
| 122 |
"count": 20
|
| 123 |
},
|
| 124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
| 125 |
+
"value": 26.068181818181817,
|
| 126 |
+
"min": 3.477272727272727,
|
| 127 |
+
"max": 26.454545454545453,
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
+
"value": 1147.0,
|
| 132 |
+
"min": 153.0,
|
| 133 |
+
"max": 1455.0,
|
| 134 |
"count": 20
|
| 135 |
},
|
| 136 |
"SnowballTarget.IsTraining.mean": {
|
|
|
|
| 148 |
},
|
| 149 |
"metadata": {
|
| 150 |
"timer_format_version": "0.1.0",
|
| 151 |
+
"start_time_seconds": "1682812050",
|
| 152 |
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
|
| 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": "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": "1682812513"
|
| 160 |
},
|
| 161 |
+
"total": 463.1760118100001,
|
| 162 |
"count": 1,
|
| 163 |
+
"self": 0.4289063120004357,
|
| 164 |
"children": {
|
| 165 |
"run_training.setup": {
|
| 166 |
+
"total": 0.03837099399993349,
|
| 167 |
"count": 1,
|
| 168 |
+
"self": 0.03837099399993349
|
| 169 |
},
|
| 170 |
"TrainerController.start_learning": {
|
| 171 |
+
"total": 462.7087345039997,
|
| 172 |
"count": 1,
|
| 173 |
+
"self": 0.5385953640020489,
|
| 174 |
"children": {
|
| 175 |
"TrainerController._reset_env": {
|
| 176 |
+
"total": 4.172746314999813,
|
| 177 |
"count": 1,
|
| 178 |
+
"self": 4.172746314999813
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
+
"total": 457.8549318849982,
|
| 182 |
+
"count": 18201,
|
| 183 |
+
"self": 0.2550296910126235,
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
+
"total": 457.5999021939856,
|
| 187 |
+
"count": 18201,
|
| 188 |
+
"self": 330.0173683849714,
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
+
"total": 127.3173148870028,
|
| 192 |
+
"count": 18201,
|
| 193 |
+
"self": 1.6640490720171783,
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
+
"total": 125.65326581498562,
|
| 197 |
+
"count": 18201,
|
| 198 |
+
"self": 125.65326581498562
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
+
"total": 0.2652189220113996,
|
| 204 |
+
"count": 18201,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
+
"total": 461.2052560590121,
|
| 209 |
+
"count": 18201,
|
| 210 |
"is_parallel": true,
|
| 211 |
+
"self": 219.11800254700552,
|
| 212 |
"children": {
|
| 213 |
"run_training.setup": {
|
| 214 |
"total": 0.0,
|
|
|
|
| 217 |
"self": 0.0,
|
| 218 |
"children": {
|
| 219 |
"steps_from_proto": {
|
| 220 |
+
"total": 0.001698680999879798,
|
| 221 |
"count": 1,
|
| 222 |
"is_parallel": true,
|
| 223 |
+
"self": 0.0004412959995079291,
|
| 224 |
"children": {
|
| 225 |
"_process_rank_one_or_two_observation": {
|
| 226 |
+
"total": 0.001257385000371869,
|
| 227 |
"count": 10,
|
| 228 |
"is_parallel": true,
|
| 229 |
+
"self": 0.001257385000371869
|
| 230 |
}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
"UnityEnvironment.step": {
|
| 234 |
+
"total": 0.06310810099989794,
|
| 235 |
"count": 1,
|
| 236 |
"is_parallel": true,
|
| 237 |
+
"self": 0.0006132109997452062,
|
| 238 |
"children": {
|
| 239 |
"UnityEnvironment._generate_step_input": {
|
| 240 |
+
"total": 0.00040094700011650275,
|
| 241 |
"count": 1,
|
| 242 |
"is_parallel": true,
|
| 243 |
+
"self": 0.00040094700011650275
|
| 244 |
},
|
| 245 |
"communicator.exchange": {
|
| 246 |
+
"total": 0.060244443000101455,
|
| 247 |
"count": 1,
|
| 248 |
"is_parallel": true,
|
| 249 |
+
"self": 0.060244443000101455
|
| 250 |
},
|
| 251 |
"steps_from_proto": {
|
| 252 |
+
"total": 0.0018494999999347783,
|
| 253 |
"count": 1,
|
| 254 |
"is_parallel": true,
|
| 255 |
+
"self": 0.00034565299961286655,
|
| 256 |
"children": {
|
| 257 |
"_process_rank_one_or_two_observation": {
|
| 258 |
+
"total": 0.0015038470003219118,
|
| 259 |
"count": 10,
|
| 260 |
"is_parallel": true,
|
| 261 |
+
"self": 0.0015038470003219118
|
| 262 |
}
|
| 263 |
}
|
| 264 |
}
|
|
|
|
| 267 |
}
|
| 268 |
},
|
| 269 |
"UnityEnvironment.step": {
|
| 270 |
+
"total": 242.08725351200655,
|
| 271 |
+
"count": 18200,
|
| 272 |
"is_parallel": true,
|
| 273 |
+
"self": 9.050058720964898,
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
+
"total": 5.328109216068242,
|
| 277 |
+
"count": 18200,
|
| 278 |
"is_parallel": true,
|
| 279 |
+
"self": 5.328109216068242
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
+
"total": 196.14354363698885,
|
| 283 |
+
"count": 18200,
|
| 284 |
"is_parallel": true,
|
| 285 |
+
"self": 196.14354363698885
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
+
"total": 31.565541937984563,
|
| 289 |
+
"count": 18200,
|
| 290 |
"is_parallel": true,
|
| 291 |
+
"self": 6.067360436101808,
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
+
"total": 25.498181501882755,
|
| 295 |
+
"count": 182000,
|
| 296 |
"is_parallel": true,
|
| 297 |
+
"self": 25.498181501882755
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
|
|
| 309 |
}
|
| 310 |
},
|
| 311 |
"trainer_threads": {
|
| 312 |
+
"total": 0.00010752199978014687,
|
| 313 |
"count": 1,
|
| 314 |
+
"self": 0.00010752199978014687,
|
| 315 |
"children": {
|
| 316 |
"thread_root": {
|
| 317 |
"total": 0.0,
|
|
|
|
| 320 |
"self": 0.0,
|
| 321 |
"children": {
|
| 322 |
"trainer_advance": {
|
| 323 |
+
"total": 454.34726448795686,
|
| 324 |
+
"count": 415525,
|
| 325 |
"is_parallel": true,
|
| 326 |
+
"self": 9.69620144298483,
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
+
"total": 248.06276390497283,
|
| 330 |
+
"count": 415525,
|
| 331 |
"is_parallel": true,
|
| 332 |
+
"self": 247.29963225097322,
|
| 333 |
"children": {
|
| 334 |
"RLTrainer._checkpoint": {
|
| 335 |
+
"total": 0.7631316539996078,
|
| 336 |
"count": 4,
|
| 337 |
"is_parallel": true,
|
| 338 |
+
"self": 0.7631316539996078
|
| 339 |
}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"_update_policy": {
|
| 343 |
+
"total": 196.5882991399992,
|
| 344 |
"count": 90,
|
| 345 |
"is_parallel": true,
|
| 346 |
+
"self": 73.88801871199598,
|
| 347 |
"children": {
|
| 348 |
"TorchPPOOptimizer.update": {
|
| 349 |
+
"total": 122.70028042800323,
|
| 350 |
"count": 4587,
|
| 351 |
"is_parallel": true,
|
| 352 |
+
"self": 122.70028042800323
|
| 353 |
}
|
| 354 |
}
|
| 355 |
}
|
|
|
|
| 360 |
}
|
| 361 |
},
|
| 362 |
"TrainerController._save_models": {
|
| 363 |
+
"total": 0.1423534179998569,
|
| 364 |
"count": 1,
|
| 365 |
+
"self": 0.000910533000023861,
|
| 366 |
"children": {
|
| 367 |
"RLTrainer._checkpoint": {
|
| 368 |
+
"total": 0.14144288499983304,
|
| 369 |
"count": 1,
|
| 370 |
+
"self": 0.14144288499983304
|
| 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": 1682812169.7190106,
|
| 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": 21.272727272727273,
|
| 17 |
+
"creation_time": 1682812285.0583925,
|
| 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": 25.818181818181817,
|
| 26 |
+
"creation_time": 1682812401.0029347,
|
| 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": 25.727272727272727,
|
| 35 |
+
"creation_time": 1682812513.170995,
|
| 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": 25.727272727272727,
|
| 44 |
+
"creation_time": 1682812513.3344672,
|
| 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": 25.727272727272727,
|
| 54 |
+
"creation_time": 1682812513.3344672,
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
|
| 57 |
]
|
| 58 |
}
|
| 59 |
},
|