Hugging Face's logo

DrishtiSharma
/
ppo-Pyramids

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Model card Files
xet
Metrics Community
DrishtiSharma commited on
Commit
462d536
·
1 Parent(s): 62da25f

Upload Pyramids.ipynb

Browse files
Files changed (1) hide show
  1. Pyramids.ipynb +589 -0
Pyramids.ipynb ADDED
@@ -0,0 +1,589 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ }
15
+ },
16
+ "cells": [
17
+ {
18
+ "cell_type": "code",
19
+ "source": [
20
+ "%%capture\n",
21
+ "# Clone the repository\n",
22
+ "!git clone --depth 1 --branch hf-integration https://github.com/huggingface/ml-agents"
23
+ ],
24
+ "metadata": {
25
+ "id": "G4mCAG8VD-IC"
26
+ },
27
+ "execution_count": 2,
28
+ "outputs": []
29
+ },
30
+ {
31
+ "cell_type": "code",
32
+ "source": [
33
+ "%%capture\n",
34
+ "# Go inside the repository and install the package\n",
35
+ "%cd ml-agents\n",
36
+ "!pip3 install -e ./ml-agents-envs\n",
37
+ "!pip3 install -e ./ml-agents"
38
+ ],
39
+ "metadata": {
40
+ "id": "NcpEBgG4ETH2"
41
+ },
42
+ "execution_count": 3,
43
+ "outputs": []
44
+ },
45
+ {
46
+ "cell_type": "code",
47
+ "source": [
48
+ "# Here, we create training-envs-executables and linux\n",
49
+ "!mkdir ./training-envs-executables\n",
50
+ "!mkdir ./training-envs-executables/linux"
51
+ ],
52
+ "metadata": {
53
+ "id": "lXhbEf4uEYL8"
54
+ },
55
+ "execution_count": 4,
56
+ "outputs": []
57
+ },
58
+ {
59
+ "cell_type": "code",
60
+ "source": [
61
+ "\n",
62
+ "!wget --load-cookies /tmp/cookies.txt \"https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1UiFNdKlsH0NTu32xV-giYUEVKV4-vc7H' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\\1\\n/p')&id=1UiFNdKlsH0NTu32xV-giYUEVKV4-vc7H\" -O ./training-envs-executables/linux/Pyramids.zip && rm -rf /tmp/cookies.txt"
63
+ ],
64
+ "metadata": {
65
+ "colab": {
66
+ "base_uri": "https://localhost:8080/"
67
+ },
68
+ "id": "uLDPaf0PFAsO",
69
+ "outputId": "0eb271bb-6847-434a-c86b-037f4bbc4ae4"
70
+ },
71
+ "execution_count": 8,
72
+ "outputs": [
73
+ {
74
+ "output_type": "stream",
75
+ "name": "stdout",
76
+ "text": [
77
+ "--2023-03-29 06:35:26-- https://docs.google.com/uc?export=download&confirm=t&id=1UiFNdKlsH0NTu32xV-giYUEVKV4-vc7H\n",
78
+ "Resolving docs.google.com (docs.google.com)... 74.125.124.101, 74.125.124.102, 74.125.124.100, ...\n",
79
+ "Connecting to docs.google.com (docs.google.com)|74.125.124.101|:443... connected.\n",
80
+ "HTTP request sent, awaiting response... 303 See Other\n",
81
+ "Location: https://doc-04-8c-docs.googleusercontent.com/docs/securesc/ha0ro937gcuc7l7deffksulhg5h7mbp1/rjm8bjnjjbaceuunacqhu0f96cocc32v/1680071700000/09764732090272539193/*/1UiFNdKlsH0NTu32xV-giYUEVKV4-vc7H?e=download&uuid=29de938c-bba9-4c4e-ab49-c669aefc08dc [following]\n",
82
+ "Warning: wildcards not supported in HTTP.\n",
83
+ "--2023-03-29 06:35:26-- https://doc-04-8c-docs.googleusercontent.com/docs/securesc/ha0ro937gcuc7l7deffksulhg5h7mbp1/rjm8bjnjjbaceuunacqhu0f96cocc32v/1680071700000/09764732090272539193/*/1UiFNdKlsH0NTu32xV-giYUEVKV4-vc7H?e=download&uuid=29de938c-bba9-4c4e-ab49-c669aefc08dc\n",
84
+ "Resolving doc-04-8c-docs.googleusercontent.com (doc-04-8c-docs.googleusercontent.com)... 142.250.159.132, 2607:f8b0:4001:c58::84\n",
85
+ "Connecting to doc-04-8c-docs.googleusercontent.com (doc-04-8c-docs.googleusercontent.com)|142.250.159.132|:443... connected.\n",
86
+ "HTTP request sent, awaiting response... 200 OK\n",
87
+ "Length: 42907187 (41M) [application/zip]\n",
88
+ "Saving to: ‘./training-envs-executables/linux/Pyramids.zip’\n",
89
+ "\n",
90
+ "./training-envs-exe 100%[===================>] 40.92M 150MB/s in 0.3s \n",
91
+ "\n",
92
+ "2023-03-29 06:35:26 (150 MB/s) - ‘./training-envs-executables/linux/Pyramids.zip’ saved [42907187/42907187]\n",
93
+ "\n"
94
+ ]
95
+ }
96
+ ]
97
+ },
98
+ {
99
+ "cell_type": "code",
100
+ "source": [
101
+ "%%capture\n",
102
+ "!unzip -d ./training-envs-executables/linux/ ./training-envs-executables/linux/Pyramids.zip"
103
+ ],
104
+ "metadata": {
105
+ "id": "mYB8LtCgD41b"
106
+ },
107
+ "execution_count": 9,
108
+ "outputs": []
109
+ },
110
+ {
111
+ "cell_type": "code",
112
+ "source": [
113
+ "!chmod -R 755 ./training-envs-executables/linux/Pyramids/Pyramids"
114
+ ],
115
+ "metadata": {
116
+ "id": "xwUAhMU7EDOx"
117
+ },
118
+ "execution_count": null,
119
+ "outputs": []
120
+ },
121
+ {
122
+ "cell_type": "code",
123
+ "source": [
124
+ "!mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=\"Pyramids Training\" --no-graphics"
125
+ ],
126
+ "metadata": {
127
+ "colab": {
128
+ "base_uri": "https://localhost:8080/"
129
+ },
130
+ "id": "s-73GPpPEHDl",
131
+ "outputId": "351b355b-728e-4dae-a941-482c272d64d0"
132
+ },
133
+ "execution_count": 10,
134
+ "outputs": [
135
+ {
136
+ "output_type": "stream",
137
+ "name": "stdout",
138
+ "text": [
139
+ "\n",
140
+ " ┐ ╖\n",
141
+ " ╓╖╬│╡ ││╬╖╖\n",
142
+ " ╓╖╬│││││┘ ╬│││││╬╖\n",
143
+ " ╖╬│││││╬╜ ╙╬│││││╖╖ ╗╗╗\n",
144
+ " ╬╬╬╬╖││╦╖ ╖╬││╗╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╜╜╜ ╟╣╣\n",
145
+ " ╬╬╬╬╬╬╬╬╖│╬╖╖╓╬╪│╓╣╣╣╣╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╒╣╣╖╗╣╣╣╗ ╣╣╣ ╣╣╣╣╣╣ ╟╣╣╖ ╣╣╣\n",
146
+ " ╬╬╬╬┐ ╙╬╬╬╬│╓╣╣╣╝╜ ╫╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╟╣╣╣╙ ╙╣╣╣ ╣╣╣ ╙╟╣╣╜╙ ╫╣╣ ╟╣╣\n",
147
+ " ╬╬╬╬┐ ╙╬╬╣╣ ╫╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╟╣╣╬ ╣╣╣ ╣╣╣ ╟╣╣ ╣╣╣┌╣╣╜\n",
148
+ " ╬╬╬╜ ╬╬╣╣ ╙╝╣╣╬ ╙╣╣╣╗╖╓╗╣╣╣╜ ╟╣╣╬ ╣╣╣ ╣╣╣ ╟╣╣╦╓ ╣╣╣╣╣\n",
149
+ " ╙ ╓╦╖ ╬╬╣╣ ╓╗╗╖ ╙╝╣╣╣╣╝╜ ╘╝╝╜ ╝╝╝ ╝╝╝ ╙╣╣╣ ╟╣╣╣\n",
150
+ " ╩╬╬╬╬╬╬╦╦╬╬╣╣╗╣╣╣╣╣╣╣╝ ╫╣╣╣╣\n",
151
+ " ╙╬╬╬╬╬╬╬╣╣╣╣╣╣╝╜\n",
152
+ " ╙╬╬╬╣╣╣╜\n",
153
+ " ╙\n",
154
+ " \n",
155
+ " Version information:\n",
156
+ " ml-agents: 0.31.0.dev0,\n",
157
+ " ml-agents-envs: 0.31.0.dev0,\n",
158
+ " Communicator API: 1.5.0,\n",
159
+ " PyTorch: 1.11.0+cu102\n",
160
+ "[INFO] Connected to Unity environment with package version 2.2.1-exp.1 and communication version 1.5.0\n",
161
+ "[INFO] Connected new brain: Pyramids?team=0\n",
162
+ "2023-03-29 06:36:53.359663: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
163
+ "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
164
+ "2023-03-29 06:36:58.264300: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
165
+ "2023-03-29 06:36:58.266029: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
166
+ "2023-03-29 06:36:58.266820: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n",
167
+ "[INFO] Hyperparameters for behavior name Pyramids: \n",
168
+ "\ttrainer_type:\tppo\n",
169
+ "\thyperparameters:\t\n",
170
+ "\t batch_size:\t128\n",
171
+ "\t buffer_size:\t2048\n",
172
+ "\t learning_rate:\t0.0003\n",
173
+ "\t beta:\t0.01\n",
174
+ "\t epsilon:\t0.2\n",
175
+ "\t lambd:\t0.95\n",
176
+ "\t num_epoch:\t3\n",
177
+ "\t shared_critic:\tFalse\n",
178
+ "\t learning_rate_schedule:\tlinear\n",
179
+ "\t beta_schedule:\tlinear\n",
180
+ "\t epsilon_schedule:\tlinear\n",
181
+ "\tcheckpoint_interval:\t500000\n",
182
+ "\tnetwork_settings:\t\n",
183
+ "\t normalize:\tFalse\n",
184
+ "\t hidden_units:\t512\n",
185
+ "\t num_layers:\t2\n",
186
+ "\t vis_encode_type:\tsimple\n",
187
+ "\t memory:\tNone\n",
188
+ "\t goal_conditioning_type:\thyper\n",
189
+ "\t deterministic:\tFalse\n",
190
+ "\treward_signals:\t\n",
191
+ "\t extrinsic:\t\n",
192
+ "\t gamma:\t0.99\n",
193
+ "\t strength:\t1.0\n",
194
+ "\t network_settings:\t\n",
195
+ "\t normalize:\tFalse\n",
196
+ "\t hidden_units:\t128\n",
197
+ "\t num_layers:\t2\n",
198
+ "\t vis_encode_type:\tsimple\n",
199
+ "\t memory:\tNone\n",
200
+ "\t goal_conditioning_type:\thyper\n",
201
+ "\t deterministic:\tFalse\n",
202
+ "\t rnd:\t\n",
203
+ "\t gamma:\t0.99\n",
204
+ "\t strength:\t0.01\n",
205
+ "\t network_settings:\t\n",
206
+ "\t normalize:\tFalse\n",
207
+ "\t hidden_units:\t64\n",
208
+ "\t num_layers:\t3\n",
209
+ "\t vis_encode_type:\tsimple\n",
210
+ "\t memory:\tNone\n",
211
+ "\t goal_conditioning_type:\thyper\n",
212
+ "\t deterministic:\tFalse\n",
213
+ "\t learning_rate:\t0.0001\n",
214
+ "\t encoding_size:\tNone\n",
215
+ "\tinit_path:\tNone\n",
216
+ "\tkeep_checkpoints:\t5\n",
217
+ "\teven_checkpoints:\tFalse\n",
218
+ "\tmax_steps:\t3000000\n",
219
+ "\ttime_horizon:\t128\n",
220
+ "\tsummary_freq:\t30000\n",
221
+ "\tthreaded:\tFalse\n",
222
+ "\tself_play:\tNone\n",
223
+ "\tbehavioral_cloning:\tNone\n",
224
+ "[INFO] Pyramids. Step: 30000. Time Elapsed: 101.455 s. Mean Reward: -0.872. Std of Reward: 0.514. Training.\n",
225
+ "[INFO] Pyramids. Step: 60000. Time Elapsed: 199.014 s. Mean Reward: -0.933. Std of Reward: 0.368. Training.\n",
226
+ "[INFO] Pyramids. Step: 90000. Time Elapsed: 300.673 s. Mean Reward: -0.863. Std of Reward: 0.529. Training.\n",
227
+ "[INFO] Pyramids. Step: 120000. Time Elapsed: 400.459 s. Mean Reward: -0.850. Std of Reward: 0.583. Training.\n",
228
+ "[INFO] Pyramids. Step: 150000. Time Elapsed: 504.687 s. Mean Reward: -0.581. Std of Reward: 0.894. Training.\n",
229
+ "[INFO] Pyramids. Step: 180000. Time Elapsed: 612.085 s. Mean Reward: -0.855. Std of Reward: 0.559. Training.\n",
230
+ "[INFO] Pyramids. Step: 210000. Time Elapsed: 717.356 s. Mean Reward: -0.404. Std of Reward: 1.000. Training.\n",
231
+ "[INFO] Pyramids. Step: 240000. Time Elapsed: 823.675 s. Mean Reward: -0.597. Std of Reward: 0.936. Training.\n",
232
+ "[INFO] Pyramids. Step: 270000. Time Elapsed: 927.453 s. Mean Reward: -0.514. Std of Reward: 0.959. Training.\n",
233
+ "[INFO] Pyramids. Step: 300000. Time Elapsed: 1026.001 s. Mean Reward: -0.525. Std of Reward: 0.968. Training.\n",
234
+ "[INFO] Pyramids. Step: 330000. Time Elapsed: 1126.188 s. Mean Reward: -0.349. Std of Reward: 1.075. Training.\n",
235
+ "[INFO] Pyramids. Step: 360000. Time Elapsed: 1230.222 s. Mean Reward: 0.189. Std of Reward: 1.232. Training.\n",
236
+ "[INFO] Pyramids. Step: 390000. Time Elapsed: 1334.848 s. Mean Reward: 0.015. Std of Reward: 1.212. Training.\n",
237
+ "[INFO] Pyramids. Step: 420000. Time Elapsed: 1448.564 s. Mean Reward: 0.789. Std of Reward: 1.101. Training.\n",
238
+ "[INFO] Pyramids. Step: 450000. Time Elapsed: 1570.904 s. Mean Reward: 1.062. Std of Reward: 0.976. Training.\n",
239
+ "[INFO] Pyramids. Step: 480000. Time Elapsed: 1689.276 s. Mean Reward: 1.207. Std of Reward: 0.893. Training.\n",
240
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-499916.onnx\n",
241
+ "[INFO] Pyramids. Step: 510000. Time Elapsed: 1806.577 s. Mean Reward: 1.311. Std of Reward: 0.847. Training.\n",
242
+ "[INFO] Pyramids. Step: 540000. Time Elapsed: 1920.003 s. Mean Reward: 1.129. Std of Reward: 0.993. Training.\n",
243
+ "[INFO] Pyramids. Step: 570000. Time Elapsed: 2037.317 s. Mean Reward: 1.326. Std of Reward: 0.800. Training.\n",
244
+ "[INFO] Pyramids. Step: 600000. Time Elapsed: 2159.034 s. Mean Reward: 1.396. Std of Reward: 0.709. Training.\n",
245
+ "[INFO] Pyramids. Step: 630000. Time Elapsed: 2277.282 s. Mean Reward: 1.261. Std of Reward: 0.901. Training.\n",
246
+ "[INFO] Pyramids. Step: 660000. Time Elapsed: 2410.636 s. Mean Reward: 1.548. Std of Reward: 0.543. Training.\n",
247
+ "[INFO] Pyramids. Step: 690000. Time Elapsed: 2553.031 s. Mean Reward: 1.605. Std of Reward: 0.506. Training.\n",
248
+ "[INFO] Pyramids. Step: 720000. Time Elapsed: 2695.693 s. Mean Reward: 1.661. Std of Reward: 0.410. Training.\n",
249
+ "[INFO] Pyramids. Step: 750000. Time Elapsed: 2832.742 s. Mean Reward: 1.621. Std of Reward: 0.504. Training.\n",
250
+ "[INFO] Pyramids. Step: 780000. Time Elapsed: 2960.088 s. Mean Reward: 1.627. Std of Reward: 0.433. Training.\n",
251
+ "[INFO] Pyramids. Step: 810000. Time Elapsed: 3089.164 s. Mean Reward: 1.628. Std of Reward: 0.340. Training.\n",
252
+ "[INFO] Pyramids. Step: 840000. Time Elapsed: 3224.046 s. Mean Reward: 1.569. Std of Reward: 0.583. Training.\n",
253
+ "[INFO] Pyramids. Step: 870000. Time Elapsed: 3361.922 s. Mean Reward: 1.666. Std of Reward: 0.407. Training.\n",
254
+ "[INFO] Pyramids. Step: 900000. Time Elapsed: 3491.083 s. Mean Reward: 1.700. Std of Reward: 0.391. Training.\n",
255
+ "[INFO] Pyramids. Step: 930000. Time Elapsed: 3622.705 s. Mean Reward: 1.674. Std of Reward: 0.328. Training.\n",
256
+ "[INFO] Pyramids. Step: 960000. Time Elapsed: 3748.747 s. Mean Reward: 1.663. Std of Reward: 0.420. Training.\n",
257
+ "[INFO] Pyramids. Step: 990000. Time Elapsed: 3884.888 s. Mean Reward: 1.720. Std of Reward: 0.186. Training.\n",
258
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-999942.onnx\n",
259
+ "[INFO] Pyramids. Step: 1020000. Time Elapsed: 4022.687 s. Mean Reward: 1.743. Std of Reward: 0.283. Training.\n",
260
+ "[INFO] Pyramids. Step: 1050000. Time Elapsed: 4149.459 s. Mean Reward: 1.689. Std of Reward: 0.328. Training.\n",
261
+ "[INFO] Pyramids. Step: 1080000. Time Elapsed: 4274.465 s. Mean Reward: 1.575. Std of Reward: 0.671. Training.\n",
262
+ "[INFO] Pyramids. Step: 1110000. Time Elapsed: 4404.286 s. Mean Reward: 1.636. Std of Reward: 0.498. Training.\n",
263
+ "[INFO] Pyramids. Step: 1140000. Time Elapsed: 4533.829 s. Mean Reward: 1.686. Std of Reward: 0.395. Training.\n",
264
+ "[INFO] Pyramids. Step: 1170000. Time Elapsed: 4666.266 s. Mean Reward: 1.724. Std of Reward: 0.285. Training.\n",
265
+ "[INFO] Pyramids. Step: 1200000. Time Elapsed: 4802.121 s. Mean Reward: 1.673. Std of Reward: 0.475. Training.\n",
266
+ "[INFO] Pyramids. Step: 1230000. Time Elapsed: 4936.895 s. Mean Reward: 1.718. Std of Reward: 0.312. Training.\n",
267
+ "[INFO] Pyramids. Step: 1260000. Time Elapsed: 5075.556 s. Mean Reward: 1.630. Std of Reward: 0.588. Training.\n",
268
+ "[INFO] Pyramids. Step: 1290000. Time Elapsed: 5205.058 s. Mean Reward: 1.721. Std of Reward: 0.299. Training.\n",
269
+ "[INFO] Pyramids. Step: 1320000. Time Elapsed: 5341.708 s. Mean Reward: 1.700. Std of Reward: 0.323. Training.\n",
270
+ "[INFO] Pyramids. Step: 1350000. Time Elapsed: 5475.899 s. Mean Reward: 1.742. Std of Reward: 0.149. Training.\n",
271
+ "[INFO] Pyramids. Step: 1380000. Time Elapsed: 5604.559 s. Mean Reward: 1.652. Std of Reward: 0.549. Training.\n",
272
+ "[INFO] Pyramids. Step: 1410000. Time Elapsed: 5746.207 s. Mean Reward: 1.663. Std of Reward: 0.584. Training.\n",
273
+ "[INFO] Pyramids. Step: 1440000. Time Elapsed: 5886.518 s. Mean Reward: 1.703. Std of Reward: 0.397. Training.\n",
274
+ "[INFO] Pyramids. Step: 1470000. Time Elapsed: 6024.444 s. Mean Reward: 1.687. Std of Reward: 0.469. Training.\n",
275
+ "[INFO] Pyramids. Step: 1500000. Time Elapsed: 6162.328 s. Mean Reward: 1.722. Std of Reward: 0.297. Training.\n",
276
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-1499974.onnx\n",
277
+ "[INFO] Pyramids. Step: 1530000. Time Elapsed: 6307.136 s. Mean Reward: 1.705. Std of Reward: 0.389. Training.\n",
278
+ "[INFO] Pyramids. Step: 1560000. Time Elapsed: 6452.765 s. Mean Reward: 1.708. Std of Reward: 0.454. Training.\n",
279
+ "[INFO] Pyramids. Step: 1590000. Time Elapsed: 6584.716 s. Mean Reward: 1.665. Std of Reward: 0.483. Training.\n",
280
+ "[INFO] Pyramids. Step: 1620000. Time Elapsed: 6724.784 s. Mean Reward: 1.720. Std of Reward: 0.436. Training.\n",
281
+ "[INFO] Pyramids. Step: 1650000. Time Elapsed: 6858.409 s. Mean Reward: 1.706. Std of Reward: 0.446. Training.\n",
282
+ "[INFO] Pyramids. Step: 1680000. Time Elapsed: 6985.550 s. Mean Reward: 1.720. Std of Reward: 0.389. Training.\n",
283
+ "[INFO] Pyramids. Step: 1710000. Time Elapsed: 7119.326 s. Mean Reward: 1.710. Std of Reward: 0.439. Training.\n",
284
+ "[INFO] Pyramids. Step: 1740000. Time Elapsed: 7256.310 s. Mean Reward: 1.741. Std of Reward: 0.360. Training.\n",
285
+ "[INFO] Pyramids. Step: 1770000. Time Elapsed: 7393.341 s. Mean Reward: 1.748. Std of Reward: 0.369. Training.\n",
286
+ "[INFO] Pyramids. Step: 1800000. Time Elapsed: 7531.948 s. Mean Reward: 1.764. Std of Reward: 0.264. Training.\n",
287
+ "[INFO] Pyramids. Step: 1830000. Time Elapsed: 7666.819 s. Mean Reward: 1.760. Std of Reward: 0.276. Training.\n",
288
+ "[INFO] Pyramids. Step: 1860000. Time Elapsed: 7799.391 s. Mean Reward: 1.758. Std of Reward: 0.170. Training.\n",
289
+ "[INFO] Pyramids. Step: 1890000. Time Elapsed: 7932.572 s. Mean Reward: 1.744. Std of Reward: 0.284. Training.\n",
290
+ "[INFO] Pyramids. Step: 1920000. Time Elapsed: 8066.671 s. Mean Reward: 1.773. Std of Reward: 0.139. Training.\n",
291
+ "[INFO] Pyramids. Step: 1950000. Time Elapsed: 8207.269 s. Mean Reward: 1.768. Std of Reward: 0.161. Training.\n",
292
+ "[INFO] Pyramids. Step: 1980000. Time Elapsed: 8346.790 s. Mean Reward: 1.802. Std of Reward: 0.109. Training.\n",
293
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-1999967.onnx\n",
294
+ "[INFO] Pyramids. Step: 2010000. Time Elapsed: 8481.710 s. Mean Reward: 1.732. Std of Reward: 0.428. Training.\n",
295
+ "[INFO] Pyramids. Step: 2040000. Time Elapsed: 8613.497 s. Mean Reward: 1.703. Std of Reward: 0.448. Training.\n",
296
+ "[INFO] Pyramids. Step: 2070000. Time Elapsed: 8749.200 s. Mean Reward: 1.754. Std of Reward: 0.177. Training.\n",
297
+ "[INFO] Pyramids. Step: 2100000. Time Elapsed: 8885.866 s. Mean Reward: 1.760. Std of Reward: 0.282. Training.\n",
298
+ "[INFO] Pyramids. Step: 2130000. Time Elapsed: 9023.976 s. Mean Reward: 1.770. Std of Reward: 0.162. Training.\n",
299
+ "[INFO] Pyramids. Step: 2160000. Time Elapsed: 9166.838 s. Mean Reward: 1.742. Std of Reward: 0.410. Training.\n",
300
+ "[INFO] Pyramids. Step: 2190000. Time Elapsed: 9307.147 s. Mean Reward: 1.770. Std of Reward: 0.273. Training.\n",
301
+ "[INFO] Pyramids. Step: 2220000. Time Elapsed: 9441.487 s. Mean Reward: 1.707. Std of Reward: 0.388. Training.\n",
302
+ "[INFO] Pyramids. Step: 2250000. Time Elapsed: 9581.738 s. Mean Reward: 1.784. Std of Reward: 0.130. Training.\n",
303
+ "[INFO] Pyramids. Step: 2280000. Time Elapsed: 9719.787 s. Mean Reward: 1.757. Std of Reward: 0.274. Training.\n",
304
+ "[INFO] Pyramids. Step: 2310000. Time Elapsed: 9857.539 s. Mean Reward: 1.770. Std of Reward: 0.153. Training.\n",
305
+ "[INFO] Pyramids. Step: 2340000. Time Elapsed: 9987.205 s. Mean Reward: 1.725. Std of Reward: 0.375. Training.\n",
306
+ "[INFO] Pyramids. Step: 2370000. Time Elapsed: 10117.730 s. Mean Reward: 1.736. Std of Reward: 0.308. Training.\n",
307
+ "[INFO] Pyramids. Step: 2400000. Time Elapsed: 10252.886 s. Mean Reward: 1.733. Std of Reward: 0.373. Training.\n",
308
+ "[INFO] Pyramids. Step: 2430000. Time Elapsed: 10397.404 s. Mean Reward: 1.761. Std of Reward: 0.267. Training.\n",
309
+ "[INFO] Pyramids. Step: 2460000. Time Elapsed: 10533.164 s. Mean Reward: 1.777. Std of Reward: 0.272. Training.\n",
310
+ "[INFO] Pyramids. Step: 2490000. Time Elapsed: 10675.384 s. Mean Reward: 1.791. Std of Reward: 0.121. Training.\n",
311
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-2499954.onnx\n",
312
+ "[INFO] Pyramids. Step: 2520000. Time Elapsed: 10817.342 s. Mean Reward: 1.752. Std of Reward: 0.353. Training.\n",
313
+ "[INFO] Pyramids. Step: 2550000. Time Elapsed: 10957.949 s. Mean Reward: 1.795. Std of Reward: 0.118. Training.\n",
314
+ "[INFO] Pyramids. Step: 2580000. Time Elapsed: 11093.594 s. Mean Reward: 1.733. Std of Reward: 0.427. Training.\n",
315
+ "[INFO] Pyramids. Step: 2610000. Time Elapsed: 11227.655 s. Mean Reward: 1.716. Std of Reward: 0.449. Training.\n",
316
+ "[INFO] Pyramids. Step: 2640000. Time Elapsed: 11362.885 s. Mean Reward: 1.776. Std of Reward: 0.150. Training.\n",
317
+ "[INFO] Pyramids. Step: 2670000. Time Elapsed: 11500.539 s. Mean Reward: 1.715. Std of Reward: 0.443. Training.\n",
318
+ "[INFO] Pyramids. Step: 2700000. Time Elapsed: 11643.585 s. Mean Reward: 1.728. Std of Reward: 0.433. Training.\n",
319
+ "[INFO] Pyramids. Step: 2730000. Time Elapsed: 11778.876 s. Mean Reward: 1.760. Std of Reward: 0.280. Training.\n",
320
+ "[INFO] Pyramids. Step: 2760000. Time Elapsed: 11917.592 s. Mean Reward: 1.770. Std of Reward: 0.267. Training.\n",
321
+ "[INFO] Pyramids. Step: 2790000. Time Elapsed: 12051.461 s. Mean Reward: 1.749. Std of Reward: 0.360. Training.\n",
322
+ "[INFO] Pyramids. Step: 2820000. Time Elapsed: 12191.994 s. Mean Reward: 1.768. Std of Reward: 0.350. Training.\n",
323
+ "[INFO] Pyramids. Step: 2850000. Time Elapsed: 12319.137 s. Mean Reward: 1.681. Std of Reward: 0.522. Training.\n",
324
+ "[INFO] Pyramids. Step: 2880000. Time Elapsed: 12457.755 s. Mean Reward: 1.741. Std of Reward: 0.414. Training.\n",
325
+ "[INFO] Pyramids. Step: 2910000. Time Elapsed: 12583.409 s. Mean Reward: 1.736. Std of Reward: 0.366. Training.\n",
326
+ "[INFO] Pyramids. Step: 2940000. Time Elapsed: 12717.883 s. Mean Reward: 1.780. Std of Reward: 0.139. Training.\n",
327
+ "[INFO] Pyramids. Step: 2970000. Time Elapsed: 12853.405 s. Mean Reward: 1.773. Std of Reward: 0.268. Training.\n",
328
+ "[INFO] Pyramids. Step: 3000000. Time Elapsed: 12983.290 s. Mean Reward: 1.697. Std of Reward: 0.507. Training.\n",
329
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-2999875.onnx\n",
330
+ "[INFO] Exported results/Pyramids Training/Pyramids/Pyramids-3000131.onnx\n",
331
+ "[INFO] Copied results/Pyramids Training/Pyramids/Pyramids-3000131.onnx to results/Pyramids Training/Pyramids.onnx.\n"
332
+ ]
333
+ }
334
+ ]
335
+ },
336
+ {
337
+ "cell_type": "code",
338
+ "source": [
339
+ "!mlagents-push-to-hf --run-id=\"Pyramids Training\" --local-dir=\"/content/ml-agents/results/Pyramids Training\" --repo-id=\"DrishtiSharma/ppo-Pyramids\" --commit-message=\"First Push\""
340
+ ],
341
+ "metadata": {
342
+ "colab": {
343
+ "base_uri": "https://localhost:8080/"
344
+ },
345
+ "id": "5BHFfKX16gzn",
346
+ "outputId": "9d73f2cc-4f86-4a6a-c3d1-921028364e38"
347
+ },
348
+ "execution_count": 33,
349
+ "outputs": [
350
+ {
351
+ "output_type": "stream",
352
+ "name": "stdout",
353
+ "text": [
354
+ "/content/ml-agents/hub/ppo-Pyramids is already a clone of https://huggingface.co/DrishtiSharma/ppo-Pyramids. Make sure you pull the latest changes with `repo.git_pull()`.\n",
355
+ "WARNING:huggingface_hub.repository:/content/ml-agents/hub/ppo-Pyramids is already a clone of https://huggingface.co/DrishtiSharma/ppo-Pyramids. Make sure you pull the latest changes with `repo.git_pull()`.\n",
356
+ "Upload file Pyramids-1499974.pt: 0% 32.0k/8.25M [00:00<?, ?B/s]\n",
357
+ "Upload file Pyramids-2499954.onnx: 2% 32.0k/1.35M [00:00<?, ?B/s]\u001b[A\n",
358
+ "\n",
359
+ "Upload file Pyramids-2999875.onnx: 2% 32.0k/1.35M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
360
+ "\n",
361
+ "\n",
362
+ "Upload file Pyramids-1499974.onnx: 2% 32.0k/1.35M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\n",
363
+ "\n",
364
+ "\n",
365
+ "\n",
366
+ "Upload file Pyramids-2499954.pt: 0% 32.0k/8.25M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
367
+ "\n",
368
+ "\n",
369
+ "\n",
370
+ "\n",
371
+ "Upload file Pyramids-3000131.pt: 0% 32.0k/8.25M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
372
+ "\n",
373
+ "\n",
374
+ "\n",
375
+ "\n",
376
+ "\n",
377
+ "Upload file Pyramids-1999967.pt: 0% 32.0k/8.25M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
378
+ "\n",
379
+ "\n",
380
+ "\n",
381
+ "\n",
382
+ "\n",
383
+ "\n",
384
+ "Upload file Pyramids-2999875.pt: 0% 32.0k/8.25M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
385
+ "\n",
386
+ "\n",
387
+ "\n",
388
+ "Upload file Pyramids-2499954.pt: 17% 1.38M/8.25M [00:01<00:05, 1.40MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
389
+ "\n",
390
+ "\n",
391
+ "\n",
392
+ "\n",
393
+ "\n",
394
+ "Upload file Pyramids-1999967.pt: 17% 1.41M/8.25M [00:01<00:04, 1.44MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
395
+ "\n",
396
+ "\n",
397
+ "\n",
398
+ "\n",
399
+ "\n",
400
+ "\n",
401
+ "Upload file Pyramids-2999875.pt: 17% 1.38M/8.25M [00:01<00:05, 1.40MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
402
+ "\n",
403
+ "\n",
404
+ "\n",
405
+ "\n",
406
+ "Upload file Pyramids-1499974.pt: 22% 1.81M/8.25M [00:01<00:03, 1.86MB/s]\n",
407
+ "\n",
408
+ "\n",
409
+ "\n",
410
+ "\n",
411
+ "\n",
412
+ "\n",
413
+ "\n",
414
+ "Upload file Pyramids-1999967.onnx: 2% 32.0k/1.35M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
415
+ "\n",
416
+ "\n",
417
+ "\n",
418
+ "\n",
419
+ "\n",
420
+ "\n",
421
+ "\n",
422
+ "\n",
423
+ "Upload file Pyramids/events.out.tfevents.1680071821.5e4b33e6d482.1878.0: 4% 32.0k/885k [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
424
+ "\n",
425
+ "\n",
426
+ "\n",
427
+ "\n",
428
+ "Upload file Pyramids-3000131.pt: 50% 4.09M/8.25M [00:02<00:01, 2.25MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
429
+ "\n",
430
+ "\n",
431
+ "\n",
432
+ "\n",
433
+ "\n",
434
+ "\n",
435
+ "Upload file Pyramids-2999875.pt: 51% 4.19M/8.25M [00:02<00:01, 2.30MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
436
+ "\n",
437
+ "\n",
438
+ "\n",
439
+ "\n",
440
+ "\n",
441
+ "Upload file Pyramids-1499974.pt: 56% 4.66M/8.25M [00:02<00:01, 2.51MB/s]\n",
442
+ "\n",
443
+ "\n",
444
+ "\n",
445
+ "Upload file Pyramids-2499954.pt: 50% 4.09M/8.25M [00:02<00:01, 2.24MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
446
+ "\n",
447
+ "\n",
448
+ "\n",
449
+ "\n",
450
+ "Upload file Pyramids-1499974.pt: 93% 7.66M/8.25M [00:03<00:00, 2.79MB/s]\n",
451
+ "\n",
452
+ "\n",
453
+ "\n",
454
+ "\n",
455
+ "\n",
456
+ "\n",
457
+ "Upload file Pyramids-2999875.pt: 88% 7.28M/8.25M [00:03<00:00, 2.73MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
458
+ "\n",
459
+ "\n",
460
+ "\n",
461
+ "\n",
462
+ "\n",
463
+ "Upload file Pyramids-1999967.pt: 91% 7.50M/8.25M [00:03<00:00, 2.82MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
464
+ "\n",
465
+ "\n",
466
+ "\n",
467
+ "Upload file Pyramids-2499954.pt: 89% 7.31M/8.25M [00:03<00:00, 2.75MB/s]\u001b[A\u001b[A\u001b[A\u001b[ATo https://huggingface.co/DrishtiSharma/ppo-Pyramids\n",
468
+ " 1cfb7ee..62da25f main -> main\n",
469
+ "\n",
470
+ "WARNING:huggingface_hub.repository:To https://huggingface.co/DrishtiSharma/ppo-Pyramids\n",
471
+ " 1cfb7ee..62da25f main -> main\n",
472
+ "\n",
473
+ "Upload file Pyramids-1499974.pt: 100% 8.25M/8.25M [00:04<00:00, 2.15MB/s]\n",
474
+ "\n",
475
+ "Upload file Pyramids-2499954.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\u001b[A\n",
476
+ "Upload file Pyramids-2499954.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\n",
477
+ "\n",
478
+ "\n",
479
+ "Upload file Pyramids-2999875.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\u001b[A\u001b[A\n",
480
+ "\n",
481
+ "Upload file Pyramids-2999875.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\n",
482
+ "\n",
483
+ "\n",
484
+ "\n",
485
+ "Upload file Pyramids-1499974.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\u001b[A\u001b[A\u001b[A\n",
486
+ "\n",
487
+ "\n",
488
+ "Upload file Pyramids-1499974.onnx: 100% 1.35M/1.35M [00:04<00:00, 345kB/s]\n",
489
+ "\n",
490
+ "\n",
491
+ "\n",
492
+ "\n",
493
+ "Upload file Pyramids-2499954.pt: 100% 8.25M/8.25M [00:04<00:00, 2.05MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
494
+ "\n",
495
+ "\n",
496
+ "\n",
497
+ "Upload file Pyramids-2499954.pt: 100% 8.25M/8.25M [00:04<00:00, 2.15MB/s]\n",
498
+ "\n",
499
+ "\n",
500
+ "\n",
501
+ "\n",
502
+ "\n",
503
+ "Upload file Pyramids-3000131.pt: 100% 8.25M/8.25M [00:04<00:00, 2.07MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
504
+ "\n",
505
+ "\n",
506
+ "\n",
507
+ "\n",
508
+ "Upload file Pyramids-3000131.pt: 100% 8.25M/8.25M [00:04<00:00, 2.15MB/s]\n",
509
+ "\n",
510
+ "\n",
511
+ "\n",
512
+ "\n",
513
+ "\n",
514
+ "\n",
515
+ "Upload file Pyramids-1999967.pt: 100% 8.25M/8.25M [00:04<00:00, 2.02MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
516
+ "\n",
517
+ "\n",
518
+ "\n",
519
+ "\n",
520
+ "\n",
521
+ "Upload file Pyramids-1999967.pt: 100% 8.25M/8.25M [00:04<00:00, 2.15MB/s]\n",
522
+ "\n",
523
+ "\n",
524
+ "\n",
525
+ "\n",
526
+ "\n",
527
+ "\n",
528
+ "\n",
529
+ "Upload file Pyramids-2999875.pt: 100% 8.25M/8.25M [00:04<00:00, 2.05MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
530
+ "\n",
531
+ "\n",
532
+ "\n",
533
+ "\n",
534
+ "\n",
535
+ "\n",
536
+ "Upload file Pyramids-2999875.pt: 100% 8.25M/8.25M [00:04<00:00, 2.15MB/s]\n",
537
+ "\n",
538
+ "\n",
539
+ "\n",
540
+ "\n",
541
+ "\n",
542
+ "\n",
543
+ "\n",
544
+ "\n",
545
+ "Upload file Pyramids-1999967.onnx: 100% 1.35M/1.35M [00:03<00:00, 460kB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
546
+ "\n",
547
+ "\n",
548
+ "\n",
549
+ "\n",
550
+ "\n",
551
+ "\n",
552
+ "\n",
553
+ "Upload file Pyramids-1999967.onnx: 100% 1.35M/1.35M [00:03<00:00, 460kB/s]\n",
554
+ "\n",
555
+ "\n",
556
+ "\n",
557
+ "\n",
558
+ "\n",
559
+ "\n",
560
+ "\n",
561
+ "\n",
562
+ "\n",
563
+ "Upload file Pyramids/events.out.tfevents.1680071821.5e4b33e6d482.1878.0: 100% 885k/885k [00:03<00:00, 290kB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
564
+ "\n",
565
+ "\n",
566
+ "\n",
567
+ "\n",
568
+ "\n",
569
+ "\n",
570
+ "\n",
571
+ "\n",
572
+ "Upload file Pyramids/events.out.tfevents.1680071821.5e4b33e6d482.1878.0: 100% 885k/885k [00:03<00:00, 290kB/s]\n",
573
+ "\n",
574
+ " Your model is pushed to the hub. You can view your model here: https://huggingface.co/DrishtiSharma/ppo-Pyramids\n"
575
+ ]
576
+ }
577
+ ]
578
+ },
579
+ {
580
+ "cell_type": "code",
581
+ "source": [],
582
+ "metadata": {
583
+ "id": "MYEdml4j7JPg"
584
+ },
585
+ "execution_count": null,
586
+ "outputs": []
587
+ }
588
+ ]
589
+ }