Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use MTahaB/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use MTahaB/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="MTahaB/ppo-Pyramids" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from MTahaB/ppo-Pyramids: direct link, hf CLI and curl.
- Browser
- Download file 15.3 kB
-
https://huggingface.co/MTahaB/ppo-Pyramids/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://MTahaB/ppo-Pyramids/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/MTahaB/ppo-Pyramids/resolve/main/run_logs/timers.json
15.3 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.418652206659317, | |
| "min": 0.4169408679008484, | |
| "max": 0.4338274598121643, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 4065.9501953125, | |
| "min": 4065.583984375, | |
| "max": 4644.5810546875, | |
| "count": 14 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 306.0571428571429, | |
| "min": 272.90909090909093, | |
| "max": 451.8695652173913, | |
| "count": 14 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 10712.0, | |
| "min": 6004.0, | |
| "max": 11398.0, | |
| "count": 14 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 1639942.0, | |
| "min": 1509898.0, | |
| "max": 1639942.0, | |
| "count": 14 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 1639942.0, | |
| "min": 1509898.0, | |
| "max": 1639942.0, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.5636081695556641, | |
| "min": 0.45088130235671997, | |
| "max": 0.5636081695556641, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 53.54277420043945, | |
| "min": 38.77579116821289, | |
| "max": 53.54277420043945, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.0051646968349814415, | |
| "min": 0.0051646968349814415, | |
| "max": 0.006903149653226137, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 0.4906461834907532, | |
| "min": 0.4906461834907532, | |
| "max": 0.6221895217895508, | |
| "count": 14 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.6367828415972845, | |
| "min": 1.3797519719600677, | |
| "max": 1.7270908924666317, | |
| "count": 14 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 57.28739945590496, | |
| "min": 33.228999376297, | |
| "max": 57.28739945590496, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.6367828415972845, | |
| "min": 1.3797519719600677, | |
| "max": 1.7270908924666317, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 57.28739945590496, | |
| "min": 33.228999376297, | |
| "max": 57.28739945590496, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.02910346505897386, | |
| "min": 0.02576324062564791, | |
| "max": 0.04514626557890248, | |
| "count": 14 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 1.018621277064085, | |
| "min": 0.5667912937642541, | |
| "max": 1.1262010842037853, | |
| "count": 14 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 14 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 14 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1792777557", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/content/mlagents-env/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --results-dir=/content/drive/MyDrive/mlagents-results --resume --inference --no-graphics", | |
| "mlagents_version": "1.1.0", | |
| "mlagents_envs_version": "1.1.0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.2+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1792777862" | |
| }, | |
| "total": 304.81845833199986, | |
| "count": 1, | |
| "self": 0.6057663430001412, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.023383601999739767, | |
| "count": 1, | |
| "self": 0.023383601999739767 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 304.189308387, | |
| "count": 1, | |
| "self": 0.2904067780355035, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.917206157999317, | |
| "count": 1, | |
| "self": 1.917206157999317 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 301.9816928369646, | |
| "count": 9751, | |
| "self": 0.2916269539819041, | |
| "children": { | |
| "env_step": { | |
| "total": 281.7719331329781, | |
| "count": 9751, | |
| "self": 253.84789800992894, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 27.75555166004324, | |
| "count": 9751, | |
| "self": 0.8269524660272509, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 26.928599194015987, | |
| "count": 9418, | |
| "self": 26.928599194015987 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.1684834630059413, | |
| "count": 9750, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 303.6308062320386, | |
| "count": 9750, | |
| "is_parallel": true, | |
| "self": 70.34117099205378, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0024450740002066595, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007541399991168873, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0016909340010897722, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0016909340010897722 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05545143999916036, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007091349980328232, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005160810005691019, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005160810005691019 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.05229850700015959, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.05229850700015959 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001927717000398843, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00038422799934778595, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015434890010510571, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0015434890010510571 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 233.28963523998482, | |
| "count": 9749, | |
| "is_parallel": true, | |
| "self": 5.554930061010964, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 3.896609491954223, | |
| "count": 9749, | |
| "is_parallel": true, | |
| "self": 3.896609491954223 | |
| }, | |
| "communicator.exchange": { | |
| "total": 206.37216209101643, | |
| "count": 9749, | |
| "is_parallel": true, | |
| "self": 206.37216209101643 | |
| }, | |
| "steps_from_proto": { | |
| "total": 17.465933596003197, | |
| "count": 9749, | |
| "is_parallel": true, | |
| "self": 3.781822810901758, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 13.684110785101439, | |
| "count": 77992, | |
| "is_parallel": true, | |
| "self": 13.684110785101439 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 19.918132750004588, | |
| "count": 9750, | |
| "self": 0.6250449029839729, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 19.293087847020615, | |
| "count": 9750, | |
| "self": 18.88545066702045, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.40763718000016524, | |
| "count": 2, | |
| "self": 0.40763718000016524 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 2.6140005502384156e-06, | |
| "count": 1, | |
| "self": 2.6140005502384156e-06 | |
| } | |
| } | |
| } | |
| } | |
| } |