First training of ML-Agents Pyramids
Browse files- Pyramids.onnx +3 -0
- Pyramids/Pyramids-1499960.onnx +3 -0
- Pyramids/Pyramids-1499960.pt +3 -0
- Pyramids/Pyramids-1999993.onnx +3 -0
- Pyramids/Pyramids-1999993.pt +3 -0
- Pyramids/Pyramids-2499893.onnx +3 -0
- Pyramids/Pyramids-2499893.pt +3 -0
- Pyramids/Pyramids-2999961.onnx +3 -0
- Pyramids/Pyramids-2999961.pt +3 -0
- Pyramids/Pyramids-3000089.onnx +3 -0
- Pyramids/Pyramids-3000089.pt +3 -0
- Pyramids/checkpoint.pt +3 -0
- Pyramids/events.out.tfevents.1731688235.Christian.10232.0 +3 -0
- README.md +35 -0
- config.json +1 -0
- configuration.yaml +92 -0
- run_logs/Player-0.log +58 -0
- run_logs/timers.json +356 -0
- run_logs/training_status.json +65 -0
Pyramids.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
|
3 |
+
size 1420238
|
Pyramids/Pyramids-1499960.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7257b97ec601e2d85ee2b022fbc2a78e17360ea257a2c8850540e57d76ff8fa
|
3 |
+
size 1420238
|
Pyramids/Pyramids-1499960.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6020bf5b66215f7e8c41b351ca1614101c5e1eff3ea50473b3ea7e6fd6032b39
|
3 |
+
size 8656252
|
Pyramids/Pyramids-1999993.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58338abaec209b7845a2a70994a772515337d4aaa7f894538aed5771928f4155
|
3 |
+
size 1420238
|
Pyramids/Pyramids-1999993.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709a21fbc55258706115e5e108d0d8b7e0242b6ef824de22d55426c51f2d5b99
|
3 |
+
size 8656252
|
Pyramids/Pyramids-2499893.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fbdd931f9937d1c15651d5d4247f6f01898f07aa63adeb7c28286fa685ca66b
|
3 |
+
size 1420238
|
Pyramids/Pyramids-2499893.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f7858df59282a9486738992bf7d6edd5fbef8f94306114328b2b569337c54d
|
3 |
+
size 8656252
|
Pyramids/Pyramids-2999961.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
|
3 |
+
size 1420238
|
Pyramids/Pyramids-2999961.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56f9f44718309f7799103cf8e5462a341aac1a89356ac27257733eb7348c0af2
|
3 |
+
size 8656252
|
Pyramids/Pyramids-3000089.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99291eb6815c4bc4d05acbe2f47692aee2fa6b639129cadd30d0ecdf3c364d86
|
3 |
+
size 1420238
|
Pyramids/Pyramids-3000089.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f446483435fd7e0c1a4c6c39566d05f90c3e4f8acd3d9f73872b644b473b6589
|
3 |
+
size 8656252
|
Pyramids/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6488ec5dc1c88bc3352c384288f1d41436a8f34a4f34027f077106eb51eda21
|
3 |
+
size 8655778
|
Pyramids/events.out.tfevents.1731688235.Christian.10232.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a34f5bc9e241a0e712fd9c54669e9d0f384e86017be34e13e00a8f72272d9a4b
|
3 |
+
size 848952
|
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: ml-agents
|
3 |
+
tags:
|
4 |
+
- Pyramids
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- ML-Agents-Pyramids
|
8 |
+
---
|
9 |
+
|
10 |
+
# **ppo** Agent playing **Pyramids**
|
11 |
+
This is a trained model of a **ppo** agent playing **Pyramids**
|
12 |
+
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
13 |
+
|
14 |
+
## Usage (with ML-Agents)
|
15 |
+
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
|
16 |
+
|
17 |
+
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
18 |
+
- A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your
|
19 |
+
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
|
20 |
+
- A *longer tutorial* to understand how works ML-Agents:
|
21 |
+
https://huggingface.co/learn/deep-rl-course/unit5/introduction
|
22 |
+
|
23 |
+
### Resume the training
|
24 |
+
```bash
|
25 |
+
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
26 |
+
```
|
27 |
+
|
28 |
+
### Watch your Agent play
|
29 |
+
You can watch your agent **playing directly in your browser**
|
30 |
+
|
31 |
+
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
|
32 |
+
2. Step 1: Find your model_id: ch-bz/ppo-Pyramids-v1
|
33 |
+
3. Step 2: Select your *.nn /*.onnx file
|
34 |
+
4. Click on Watch the agent play
|
35 |
+
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./build/UnityEnvironment", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "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
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_settings: null
|
2 |
+
behaviors:
|
3 |
+
Pyramids:
|
4 |
+
trainer_type: ppo
|
5 |
+
hyperparameters:
|
6 |
+
batch_size: 128
|
7 |
+
buffer_size: 2048
|
8 |
+
learning_rate: 0.0003
|
9 |
+
beta: 0.01
|
10 |
+
epsilon: 0.2
|
11 |
+
lambd: 0.95
|
12 |
+
num_epoch: 3
|
13 |
+
shared_critic: false
|
14 |
+
learning_rate_schedule: linear
|
15 |
+
beta_schedule: linear
|
16 |
+
epsilon_schedule: linear
|
17 |
+
checkpoint_interval: 500000
|
18 |
+
network_settings:
|
19 |
+
normalize: false
|
20 |
+
hidden_units: 512
|
21 |
+
num_layers: 2
|
22 |
+
vis_encode_type: simple
|
23 |
+
memory: null
|
24 |
+
goal_conditioning_type: hyper
|
25 |
+
deterministic: false
|
26 |
+
reward_signals:
|
27 |
+
extrinsic:
|
28 |
+
gamma: 0.99
|
29 |
+
strength: 1.0
|
30 |
+
network_settings:
|
31 |
+
normalize: false
|
32 |
+
hidden_units: 128
|
33 |
+
num_layers: 2
|
34 |
+
vis_encode_type: simple
|
35 |
+
memory: null
|
36 |
+
goal_conditioning_type: hyper
|
37 |
+
deterministic: false
|
38 |
+
rnd:
|
39 |
+
gamma: 0.99
|
40 |
+
strength: 0.01
|
41 |
+
network_settings:
|
42 |
+
normalize: false
|
43 |
+
hidden_units: 64
|
44 |
+
num_layers: 3
|
45 |
+
vis_encode_type: simple
|
46 |
+
memory: null
|
47 |
+
goal_conditioning_type: hyper
|
48 |
+
deterministic: false
|
49 |
+
learning_rate: 0.0001
|
50 |
+
encoding_size: null
|
51 |
+
init_path: null
|
52 |
+
keep_checkpoints: 5
|
53 |
+
even_checkpoints: false
|
54 |
+
max_steps: 3000000
|
55 |
+
time_horizon: 128
|
56 |
+
summary_freq: 30000
|
57 |
+
threaded: false
|
58 |
+
self_play: null
|
59 |
+
behavioral_cloning: null
|
60 |
+
env_settings:
|
61 |
+
env_path: ./build/UnityEnvironment
|
62 |
+
env_args: null
|
63 |
+
base_port: 5005
|
64 |
+
num_envs: 1
|
65 |
+
num_areas: 1
|
66 |
+
timeout_wait: 60
|
67 |
+
seed: -1
|
68 |
+
max_lifetime_restarts: 10
|
69 |
+
restarts_rate_limit_n: 1
|
70 |
+
restarts_rate_limit_period_s: 60
|
71 |
+
engine_settings:
|
72 |
+
width: 84
|
73 |
+
height: 84
|
74 |
+
quality_level: 5
|
75 |
+
time_scale: 20
|
76 |
+
target_frame_rate: -1
|
77 |
+
capture_frame_rate: 60
|
78 |
+
no_graphics: true
|
79 |
+
no_graphics_monitor: false
|
80 |
+
environment_parameters: null
|
81 |
+
checkpoint_settings:
|
82 |
+
run_id: Pyramids Training
|
83 |
+
initialize_from: null
|
84 |
+
load_model: false
|
85 |
+
resume: false
|
86 |
+
force: false
|
87 |
+
train_model: false
|
88 |
+
inference: false
|
89 |
+
results_dir: results
|
90 |
+
torch_settings:
|
91 |
+
device: null
|
92 |
+
debug: false
|
run_logs/Player-0.log
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Mono path[0] = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/UnityEnvironment_Data/Managed'
|
2 |
+
Mono config path = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/MonoBleedingEdge/etc'
|
3 |
+
[Physics::Module] Initialized fallback backend.
|
4 |
+
[Physics::Module] Id: 0xdecafbad
|
5 |
+
Initialize engine version: 6000.0.26f1 (ccb7c73d2c02)
|
6 |
+
[Subsystems] Discovering subsystems at path C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/UnityEnvironment_Data/UnitySubsystems
|
7 |
+
Forcing GfxDevice: Null
|
8 |
+
GfxDevice: creating device client; kGfxThreadingModeNonThreaded
|
9 |
+
NullGfxDevice:
|
10 |
+
Version: NULL 1.0 [1.0]
|
11 |
+
Renderer: Null Device
|
12 |
+
Vendor: Unity Technologies
|
13 |
+
Begin MonoManager ReloadAssembly
|
14 |
+
- Loaded All Assemblies, in 0.119 seconds
|
15 |
+
- Finished resetting the current domain, in 0.002 seconds
|
16 |
+
[Physics::Module] Selected backend.
|
17 |
+
[Physics::Module] Name: PhysX
|
18 |
+
[Physics::Module] Id: 0xf2b8ea05
|
19 |
+
[Physics::Module] SDK Version: 4.1.2
|
20 |
+
[Physics::Module] Integration Version: 1.0.0
|
21 |
+
[Physics::Module] Threading Mode: Multi-Threaded
|
22 |
+
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
23 |
+
Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
|
24 |
+
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
25 |
+
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
26 |
+
WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
|
27 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
28 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
29 |
+
ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
30 |
+
WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
|
31 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
32 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
33 |
+
WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
|
34 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
35 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
36 |
+
ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
37 |
+
WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
|
38 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
39 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
40 |
+
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
41 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
42 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
43 |
+
ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
44 |
+
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
45 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
46 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
47 |
+
WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
|
48 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
49 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
50 |
+
ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
51 |
+
WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
|
52 |
+
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
53 |
+
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
54 |
+
UnloadTime: 0.764500 ms
|
55 |
+
Registered Communicator in Agent.
|
56 |
+
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
57 |
+
[Physics::Module] Cleanup current backned.
|
58 |
+
[Physics::Module] Id: 0xf2b8ea05
|
run_logs/timers.json
ADDED
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"Pyramids.Policy.Entropy.mean": {
|
5 |
+
"value": 0.14624297618865967,
|
6 |
+
"min": 0.14624297618865967,
|
7 |
+
"max": 1.4647560119628906,
|
8 |
+
"count": 100
|
9 |
+
},
|
10 |
+
"Pyramids.Policy.Entropy.sum": {
|
11 |
+
"value": 4429.4072265625,
|
12 |
+
"min": 4429.4072265625,
|
13 |
+
"max": 44434.83984375,
|
14 |
+
"count": 100
|
15 |
+
},
|
16 |
+
"Pyramids.Step.mean": {
|
17 |
+
"value": 2999961.0,
|
18 |
+
"min": 29952.0,
|
19 |
+
"max": 2999961.0,
|
20 |
+
"count": 100
|
21 |
+
},
|
22 |
+
"Pyramids.Step.sum": {
|
23 |
+
"value": 2999961.0,
|
24 |
+
"min": 29952.0,
|
25 |
+
"max": 2999961.0,
|
26 |
+
"count": 100
|
27 |
+
},
|
28 |
+
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 0.8048204183578491,
|
30 |
+
"min": -0.09897731989622116,
|
31 |
+
"max": 0.8590055704116821,
|
32 |
+
"count": 100
|
33 |
+
},
|
34 |
+
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 238.22683715820312,
|
36 |
+
"min": -23.853534698486328,
|
37 |
+
"max": 261.1376953125,
|
38 |
+
"count": 100
|
39 |
+
},
|
40 |
+
"Pyramids.Policy.RndValueEstimate.mean": {
|
41 |
+
"value": -0.003933842293918133,
|
42 |
+
"min": -0.027270613238215446,
|
43 |
+
"max": 0.41345709562301636,
|
44 |
+
"count": 100
|
45 |
+
},
|
46 |
+
"Pyramids.Policy.RndValueEstimate.sum": {
|
47 |
+
"value": -1.1644172668457031,
|
48 |
+
"min": -8.099371910095215,
|
49 |
+
"max": 97.98933410644531,
|
50 |
+
"count": 100
|
51 |
+
},
|
52 |
+
"Pyramids.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.07051334704668816,
|
54 |
+
"min": 0.06429423743355771,
|
55 |
+
"max": 0.07545404697173377,
|
56 |
+
"count": 100
|
57 |
+
},
|
58 |
+
"Pyramids.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.9871868586536342,
|
60 |
+
"min": 0.48659723690472106,
|
61 |
+
"max": 1.1318107045760066,
|
62 |
+
"count": 100
|
63 |
+
},
|
64 |
+
"Pyramids.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.013090788689580569,
|
66 |
+
"min": 0.00012420112438344576,
|
67 |
+
"max": 0.01626293453672487,
|
68 |
+
"count": 100
|
69 |
+
},
|
70 |
+
"Pyramids.Losses.ValueLoss.sum": {
|
71 |
+
"value": 0.18327104165412797,
|
72 |
+
"min": 0.0013662123682179033,
|
73 |
+
"max": 0.24394401805087304,
|
74 |
+
"count": 100
|
75 |
+
},
|
76 |
+
"Pyramids.Policy.LearningRate.mean": {
|
77 |
+
"value": 1.5376566303380957e-06,
|
78 |
+
"min": 1.5376566303380957e-06,
|
79 |
+
"max": 0.00029838354339596195,
|
80 |
+
"count": 100
|
81 |
+
},
|
82 |
+
"Pyramids.Policy.LearningRate.sum": {
|
83 |
+
"value": 2.152719282473334e-05,
|
84 |
+
"min": 2.152719282473334e-05,
|
85 |
+
"max": 0.0037177996607335,
|
86 |
+
"count": 100
|
87 |
+
},
|
88 |
+
"Pyramids.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.10051251904761904,
|
90 |
+
"min": 0.10051251904761904,
|
91 |
+
"max": 0.19946118095238097,
|
92 |
+
"count": 100
|
93 |
+
},
|
94 |
+
"Pyramids.Policy.Epsilon.sum": {
|
95 |
+
"value": 1.4071752666666666,
|
96 |
+
"min": 1.3897045333333333,
|
97 |
+
"max": 2.737489833333334,
|
98 |
+
"count": 100
|
99 |
+
},
|
100 |
+
"Pyramids.Policy.Beta.mean": {
|
101 |
+
"value": 6.120065285714288e-05,
|
102 |
+
"min": 6.120065285714288e-05,
|
103 |
+
"max": 0.009946171977142856,
|
104 |
+
"count": 100
|
105 |
+
},
|
106 |
+
"Pyramids.Policy.Beta.sum": {
|
107 |
+
"value": 0.0008568091400000004,
|
108 |
+
"min": 0.0008568091400000004,
|
109 |
+
"max": 0.12394272335000002,
|
110 |
+
"count": 100
|
111 |
+
},
|
112 |
+
"Pyramids.Losses.RNDLoss.mean": {
|
113 |
+
"value": 0.004076735116541386,
|
114 |
+
"min": 0.004063901957124472,
|
115 |
+
"max": 0.3282770812511444,
|
116 |
+
"count": 100
|
117 |
+
},
|
118 |
+
"Pyramids.Losses.RNDLoss.sum": {
|
119 |
+
"value": 0.05707429349422455,
|
120 |
+
"min": 0.05689462646842003,
|
121 |
+
"max": 2.2979395389556885,
|
122 |
+
"count": 100
|
123 |
+
},
|
124 |
+
"Pyramids.Environment.EpisodeLength.mean": {
|
125 |
+
"value": 220.21875,
|
126 |
+
"min": 217.84285714285716,
|
127 |
+
"max": 999.0,
|
128 |
+
"count": 100
|
129 |
+
},
|
130 |
+
"Pyramids.Environment.EpisodeLength.sum": {
|
131 |
+
"value": 28188.0,
|
132 |
+
"min": 15984.0,
|
133 |
+
"max": 33669.0,
|
134 |
+
"count": 100
|
135 |
+
},
|
136 |
+
"Pyramids.Environment.CumulativeReward.mean": {
|
137 |
+
"value": 1.779781237593852,
|
138 |
+
"min": -1.0000000521540642,
|
139 |
+
"max": 1.779781237593852,
|
140 |
+
"count": 100
|
141 |
+
},
|
142 |
+
"Pyramids.Environment.CumulativeReward.sum": {
|
143 |
+
"value": 227.81199841201305,
|
144 |
+
"min": -32.000001668930054,
|
145 |
+
"max": 245.50119867920876,
|
146 |
+
"count": 100
|
147 |
+
},
|
148 |
+
"Pyramids.Policy.ExtrinsicReward.mean": {
|
149 |
+
"value": 1.779781237593852,
|
150 |
+
"min": -1.0000000521540642,
|
151 |
+
"max": 1.779781237593852,
|
152 |
+
"count": 100
|
153 |
+
},
|
154 |
+
"Pyramids.Policy.ExtrinsicReward.sum": {
|
155 |
+
"value": 227.81199841201305,
|
156 |
+
"min": -32.000001668930054,
|
157 |
+
"max": 245.50119867920876,
|
158 |
+
"count": 100
|
159 |
+
},
|
160 |
+
"Pyramids.Policy.RndReward.mean": {
|
161 |
+
"value": 0.00933070190561125,
|
162 |
+
"min": 0.009300382798619467,
|
163 |
+
"max": 6.441338911652565,
|
164 |
+
"count": 100
|
165 |
+
},
|
166 |
+
"Pyramids.Policy.RndReward.sum": {
|
167 |
+
"value": 1.19432984391824,
|
168 |
+
"min": 1.19432984391824,
|
169 |
+
"max": 103.06142258644104,
|
170 |
+
"count": 100
|
171 |
+
},
|
172 |
+
"Pyramids.IsTraining.mean": {
|
173 |
+
"value": 1.0,
|
174 |
+
"min": 1.0,
|
175 |
+
"max": 1.0,
|
176 |
+
"count": 100
|
177 |
+
},
|
178 |
+
"Pyramids.IsTraining.sum": {
|
179 |
+
"value": 1.0,
|
180 |
+
"min": 1.0,
|
181 |
+
"max": 1.0,
|
182 |
+
"count": 100
|
183 |
+
}
|
184 |
+
},
|
185 |
+
"metadata": {
|
186 |
+
"timer_format_version": "0.1.0",
|
187 |
+
"start_time_seconds": "1731688232",
|
188 |
+
"python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]",
|
189 |
+
"command_line_arguments": "C:\\Users\\songo\\Documents\\Python\\DeepRLCourse\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./build/UnityEnvironment --run-id=Pyramids Training --no-graphics",
|
190 |
+
"mlagents_version": "1.1.0",
|
191 |
+
"mlagents_envs_version": "1.1.0",
|
192 |
+
"communication_protocol_version": "1.5.0",
|
193 |
+
"pytorch_version": "2.5.1+cu124",
|
194 |
+
"numpy_version": "1.23.5",
|
195 |
+
"end_time_seconds": "1731692835"
|
196 |
+
},
|
197 |
+
"total": 4603.306294100001,
|
198 |
+
"count": 1,
|
199 |
+
"self": 0.25035030000435654,
|
200 |
+
"children": {
|
201 |
+
"run_training.setup": {
|
202 |
+
"total": 0.1570873999989999,
|
203 |
+
"count": 1,
|
204 |
+
"self": 0.1570873999989999
|
205 |
+
},
|
206 |
+
"TrainerController.start_learning": {
|
207 |
+
"total": 4602.898856399997,
|
208 |
+
"count": 1,
|
209 |
+
"self": 3.2654007006676693,
|
210 |
+
"children": {
|
211 |
+
"TrainerController._reset_env": {
|
212 |
+
"total": 4.993731700000353,
|
213 |
+
"count": 1,
|
214 |
+
"self": 4.993731700000353
|
215 |
+
},
|
216 |
+
"TrainerController.advance": {
|
217 |
+
"total": 4594.527222799328,
|
218 |
+
"count": 194290,
|
219 |
+
"self": 2.8569732006544655,
|
220 |
+
"children": {
|
221 |
+
"env_step": {
|
222 |
+
"total": 2418.813839399236,
|
223 |
+
"count": 194290,
|
224 |
+
"self": 1775.8495642986854,
|
225 |
+
"children": {
|
226 |
+
"SubprocessEnvManager._take_step": {
|
227 |
+
"total": 640.8690928998167,
|
228 |
+
"count": 194290,
|
229 |
+
"self": 9.036510999510938,
|
230 |
+
"children": {
|
231 |
+
"TorchPolicy.evaluate": {
|
232 |
+
"total": 631.8325819003057,
|
233 |
+
"count": 187570,
|
234 |
+
"self": 631.8325819003057
|
235 |
+
}
|
236 |
+
}
|
237 |
+
},
|
238 |
+
"workers": {
|
239 |
+
"total": 2.0951822007336887,
|
240 |
+
"count": 194290,
|
241 |
+
"self": 0.0,
|
242 |
+
"children": {
|
243 |
+
"worker_root": {
|
244 |
+
"total": 4595.95136709964,
|
245 |
+
"count": 194290,
|
246 |
+
"is_parallel": true,
|
247 |
+
"self": 3041.8285563000045,
|
248 |
+
"children": {
|
249 |
+
"steps_from_proto": {
|
250 |
+
"total": 0.0008488000003126217,
|
251 |
+
"count": 1,
|
252 |
+
"is_parallel": true,
|
253 |
+
"self": 0.0001990000000660075,
|
254 |
+
"children": {
|
255 |
+
"_process_rank_one_or_two_observation": {
|
256 |
+
"total": 0.0006498000002466142,
|
257 |
+
"count": 8,
|
258 |
+
"is_parallel": true,
|
259 |
+
"self": 0.0006498000002466142
|
260 |
+
}
|
261 |
+
}
|
262 |
+
},
|
263 |
+
"UnityEnvironment.step": {
|
264 |
+
"total": 1554.1219619996355,
|
265 |
+
"count": 194290,
|
266 |
+
"is_parallel": true,
|
267 |
+
"self": 51.483499799524,
|
268 |
+
"children": {
|
269 |
+
"UnityEnvironment._generate_step_input": {
|
270 |
+
"total": 34.75150880024921,
|
271 |
+
"count": 194290,
|
272 |
+
"is_parallel": true,
|
273 |
+
"self": 34.75150880024921
|
274 |
+
},
|
275 |
+
"communicator.exchange": {
|
276 |
+
"total": 1333.029609400386,
|
277 |
+
"count": 194290,
|
278 |
+
"is_parallel": true,
|
279 |
+
"self": 1333.029609400386
|
280 |
+
},
|
281 |
+
"steps_from_proto": {
|
282 |
+
"total": 134.85734399947614,
|
283 |
+
"count": 194290,
|
284 |
+
"is_parallel": true,
|
285 |
+
"self": 26.87234490111223,
|
286 |
+
"children": {
|
287 |
+
"_process_rank_one_or_two_observation": {
|
288 |
+
"total": 107.98499909836391,
|
289 |
+
"count": 1554320,
|
290 |
+
"is_parallel": true,
|
291 |
+
"self": 107.98499909836391
|
292 |
+
}
|
293 |
+
}
|
294 |
+
}
|
295 |
+
}
|
296 |
+
}
|
297 |
+
}
|
298 |
+
}
|
299 |
+
}
|
300 |
+
}
|
301 |
+
}
|
302 |
+
},
|
303 |
+
"trainer_advance": {
|
304 |
+
"total": 2172.856410199438,
|
305 |
+
"count": 194290,
|
306 |
+
"self": 6.307676598404214,
|
307 |
+
"children": {
|
308 |
+
"process_trajectory": {
|
309 |
+
"total": 351.15190310101025,
|
310 |
+
"count": 194290,
|
311 |
+
"self": 350.5796433010091,
|
312 |
+
"children": {
|
313 |
+
"RLTrainer._checkpoint": {
|
314 |
+
"total": 0.5722598000011203,
|
315 |
+
"count": 6,
|
316 |
+
"self": 0.5722598000011203
|
317 |
+
}
|
318 |
+
}
|
319 |
+
},
|
320 |
+
"_update_policy": {
|
321 |
+
"total": 1815.3968305000235,
|
322 |
+
"count": 1376,
|
323 |
+
"self": 812.0426447996033,
|
324 |
+
"children": {
|
325 |
+
"TorchPPOOptimizer.update": {
|
326 |
+
"total": 1003.3541857004202,
|
327 |
+
"count": 68484,
|
328 |
+
"self": 1003.3541857004202
|
329 |
+
}
|
330 |
+
}
|
331 |
+
}
|
332 |
+
}
|
333 |
+
}
|
334 |
+
}
|
335 |
+
},
|
336 |
+
"trainer_threads": {
|
337 |
+
"total": 6.000009307172149e-07,
|
338 |
+
"count": 1,
|
339 |
+
"self": 6.000009307172149e-07
|
340 |
+
},
|
341 |
+
"TrainerController._save_models": {
|
342 |
+
"total": 0.11250060000020312,
|
343 |
+
"count": 1,
|
344 |
+
"self": 0.03100059999997029,
|
345 |
+
"children": {
|
346 |
+
"RLTrainer._checkpoint": {
|
347 |
+
"total": 0.08150000000023283,
|
348 |
+
"count": 1,
|
349 |
+
"self": 0.08150000000023283
|
350 |
+
}
|
351 |
+
}
|
352 |
+
}
|
353 |
+
}
|
354 |
+
}
|
355 |
+
}
|
356 |
+
}
|
run_logs/training_status.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Pyramids": {
|
3 |
+
"checkpoints": [
|
4 |
+
{
|
5 |
+
"steps": 1499960,
|
6 |
+
"file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1499960.onnx",
|
7 |
+
"reward": 1.7964999992400408,
|
8 |
+
"creation_time": 1731690513.8980315,
|
9 |
+
"auxillary_file_paths": [
|
10 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-1499960.pt"
|
11 |
+
]
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"steps": 1999993,
|
15 |
+
"file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1999993.onnx",
|
16 |
+
"reward": 1.7779999990016222,
|
17 |
+
"creation_time": 1731691279.575953,
|
18 |
+
"auxillary_file_paths": [
|
19 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-1999993.pt"
|
20 |
+
]
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"steps": 2499893,
|
24 |
+
"file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2499893.onnx",
|
25 |
+
"reward": null,
|
26 |
+
"creation_time": 1731692048.6829982,
|
27 |
+
"auxillary_file_paths": [
|
28 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-2499893.pt"
|
29 |
+
]
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"steps": 2999961,
|
33 |
+
"file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-2999961.onnx",
|
34 |
+
"reward": 1.8303999781608582,
|
35 |
+
"creation_time": 1731692835.3179293,
|
36 |
+
"auxillary_file_paths": [
|
37 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-2999961.pt"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 3000089,
|
42 |
+
"file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-3000089.onnx",
|
43 |
+
"reward": 1.8303999781608582,
|
44 |
+
"creation_time": 1731692835.4158523,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-3000089.pt"
|
47 |
+
]
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"final_checkpoint": {
|
51 |
+
"steps": 3000089,
|
52 |
+
"file_path": "results\\Pyramids Training\\Pyramids.onnx",
|
53 |
+
"reward": 1.8303999781608582,
|
54 |
+
"creation_time": 1731692835.4158523,
|
55 |
+
"auxillary_file_paths": [
|
56 |
+
"results\\Pyramids Training\\Pyramids\\Pyramids-3000089.pt"
|
57 |
+
]
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"metadata": {
|
61 |
+
"stats_format_version": "0.3.0",
|
62 |
+
"mlagents_version": "1.1.0",
|
63 |
+
"torch_version": "2.5.1+cu124"
|
64 |
+
}
|
65 |
+
}
|