Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use hunter002/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use hunter002/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="hunter002/ppo-Pyramids" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from hunter002/ppo-Pyramids: direct link, hf CLI and curl.
- Browser
- Download file 18.7 kB
-
https://huggingface.co/hunter002/ppo-Pyramids/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://hunter002/ppo-Pyramids/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/hunter002/ppo-Pyramids/resolve/main/run_logs/timers.json
18.7 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5507037043571472, | |
| "min": 0.5507037043571472, | |
| "max": 1.4313383102416992, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 16424.1875, | |
| "min": 16424.1875, | |
| "max": 43421.078125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989920.0, | |
| "min": 29952.0, | |
| "max": 989920.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989920.0, | |
| "min": 29952.0, | |
| "max": 989920.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.4232293963432312, | |
| "min": -0.10670609772205353, | |
| "max": 0.4232293963432312, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 111.73255920410156, | |
| "min": -25.289344787597656, | |
| "max": 111.73255920410156, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.29871997237205505, | |
| "min": -0.2227478325366974, | |
| "max": 0.6528891324996948, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 78.86207580566406, | |
| "min": -59.25092315673828, | |
| "max": 154.73472595214844, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06857783331952177, | |
| "min": 0.06503345843827826, | |
| "max": 0.07318552045968618, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9600896664733048, | |
| "min": 0.4919940319889755, | |
| "max": 1.0395971027755877, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.03966234570397005, | |
| "min": 9.838631618061715e-05, | |
| "max": 0.03966234570397005, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.5552728398555807, | |
| "min": 0.00137740842652864, | |
| "max": 0.5552728398555807, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.386868966314285e-06, | |
| "min": 7.386868966314285e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010341616552839999, | |
| "min": 0.00010341616552839999, | |
| "max": 0.0032569109143630996, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10246225714285714, | |
| "min": 0.10246225714285714, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4344716, | |
| "min": 1.3886848, | |
| "max": 2.4432384, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002559794885714285, | |
| "min": 0.0002559794885714285, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003583712839999999, | |
| "min": 0.003583712839999999, | |
| "max": 0.10858512631, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.00957388523966074, | |
| "min": 0.00957388523966074, | |
| "max": 0.6260886788368225, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1340343952178955, | |
| "min": 0.1340343952178955, | |
| "max": 4.382620811462402, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 440.9166666666667, | |
| "min": 425.67692307692306, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 31746.0, | |
| "min": 15984.0, | |
| "max": 32833.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.336797193520599, | |
| "min": -1.0000000521540642, | |
| "max": 1.4512122838543011, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 96.24939793348312, | |
| "min": -31.997201651334763, | |
| "max": 96.24939793348312, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.336797193520599, | |
| "min": -1.0000000521540642, | |
| "max": 1.4512122838543011, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 96.24939793348312, | |
| "min": -31.997201651334763, | |
| "max": 96.24939793348312, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.04369961739899332, | |
| "min": 0.04369961739899332, | |
| "max": 13.183144208043814, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.146372452727519, | |
| "min": 3.009809620329179, | |
| "max": 210.93030732870102, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1795093942", | |
| "python_version": "3.10.22 (main, Oct 1 2026, 15:39:47) [GCC 13.3.0]", | |
| "command_line_arguments": "/content/mlagents_env/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.8.0+cu128", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1795096677" | |
| }, | |
| "total": 2734.534646125, | |
| "count": 1, | |
| "self": 0.6459327379998285, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.022632064999925205, | |
| "count": 1, | |
| "self": 0.022632064999925205 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2733.8660813220004, | |
| "count": 1, | |
| "self": 1.6482441781208763, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.1941675710004347, | |
| "count": 1, | |
| "self": 3.1941675710004347 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2728.931502461879, | |
| "count": 63362, | |
| "self": 1.705321016781454, | |
| "children": { | |
| "env_step": { | |
| "total": 1983.088724223986, | |
| "count": 63362, | |
| "self": 1799.8305440818176, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 182.28717089506245, | |
| "count": 63362, | |
| "self": 5.641209746142522, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 176.64596114891992, | |
| "count": 62554, | |
| "self": 176.64596114891992 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.9710092471059397, | |
| "count": 63362, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2727.617874854832, | |
| "count": 63362, | |
| "is_parallel": true, | |
| "self": 1066.103869320772, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0028881770003863494, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008060819991442258, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0020820950012421235, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0020820950012421235 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.11969406099979096, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006565979992956272, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004921260006085504, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004921260006085504 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.11452018999989377, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.11452018999989377 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.004025146999993012, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004252860017004423, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.00359986099829257, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.00359986099829257 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1661.5140055340598, | |
| "count": 63361, | |
| "is_parallel": true, | |
| "self": 39.62645762405646, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 28.023060026037456, | |
| "count": 63361, | |
| "is_parallel": true, | |
| "self": 28.023060026037456 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1455.4851518558971, | |
| "count": 63361, | |
| "is_parallel": true, | |
| "self": 1455.4851518558971 | |
| }, | |
| "steps_from_proto": { | |
| "total": 138.3793360280688, | |
| "count": 63361, | |
| "is_parallel": true, | |
| "self": 27.78162610437812, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 110.59770992369067, | |
| "count": 506888, | |
| "is_parallel": true, | |
| "self": 110.59770992369067 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 744.1374572211116, | |
| "count": 63362, | |
| "self": 2.9376977731890292, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 133.50218461992336, | |
| "count": 63362, | |
| "self": 133.26152771292345, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.24065690699990228, | |
| "count": 2, | |
| "self": 0.24065690699990228 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 607.6975748279992, | |
| "count": 445, | |
| "self": 334.9541375059016, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 272.74343732209763, | |
| "count": 22788, | |
| "self": 272.74343732209763 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1020001693395898e-06, | |
| "count": 1, | |
| "self": 1.1020001693395898e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09216600899981131, | |
| "count": 1, | |
| "self": 0.0012038650002068607, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09096214399960445, | |
| "count": 1, | |
| "self": 0.09096214399960445 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |