Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use debnathk/ppo-PyramidsRND with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use debnathk/ppo-PyramidsRND with ml-agents:
mlagents-load-from-hf --repo-id="debnathk/ppo-PyramidsRND" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from debnathk/ppo-PyramidsRND: direct link, hf CLI and curl.
- Browser
- Download file 18.7 kB
-
https://huggingface.co/debnathk/ppo-PyramidsRND/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://debnathk/ppo-PyramidsRND/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/debnathk/ppo-PyramidsRND/resolve/main/run_logs/timers.json
18.7 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5329424738883972, | |
| "min": 0.5329424738883972, | |
| "max": 1.486762285232544, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 15971.2197265625, | |
| "min": 15971.2197265625, | |
| "max": 45102.421875, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989964.0, | |
| "min": 29952.0, | |
| "max": 989964.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989964.0, | |
| "min": 29952.0, | |
| "max": 989964.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.2815615236759186, | |
| "min": -0.09373237937688828, | |
| "max": 0.3504044711589813, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 72.9244384765625, | |
| "min": -22.58950424194336, | |
| "max": 91.45556640625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.15907739102840424, | |
| "min": -0.030365603044629097, | |
| "max": 0.2589479684829712, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 41.201045989990234, | |
| "min": -7.925422191619873, | |
| "max": 61.37066650390625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07244354195981507, | |
| "min": 0.06586546733823834, | |
| "max": 0.07372162268344348, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.014209587437411, | |
| "min": 0.5157467815805904, | |
| "max": 1.082194048775515, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01624094249151511, | |
| "min": 0.0004921593721801216, | |
| "max": 0.01624094249151511, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.22737319488121158, | |
| "min": 0.006890231210521703, | |
| "max": 0.22737319488121158, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.4735046517214295e-06, | |
| "min": 7.4735046517214295e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010462906512410002, | |
| "min": 0.00010462906512410002, | |
| "max": 0.0036339625886791997, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10249113571428572, | |
| "min": 0.10249113571428572, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4348759000000002, | |
| "min": 1.3886848, | |
| "max": 2.6113208, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002588644578571429, | |
| "min": 0.0002588644578571429, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0036241024100000007, | |
| "min": 0.0036241024100000007, | |
| "max": 0.12115094791999999, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.006637397222220898, | |
| "min": 0.006637397222220898, | |
| "max": 0.3086859881877899, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.09292355924844742, | |
| "min": 0.09292355924844742, | |
| "max": 2.160801887512207, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 514.6101694915254, | |
| "min": 456.6617647058824, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30362.0, | |
| "min": 15984.0, | |
| "max": 32731.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.214118611635798, | |
| "min": -1.0000000521540642, | |
| "max": 1.214118611635798, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 71.63299808651209, | |
| "min": -29.864001609385014, | |
| "max": 79.4283979833126, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.214118611635798, | |
| "min": -1.0000000521540642, | |
| "max": 1.214118611635798, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 71.63299808651209, | |
| "min": -29.864001609385014, | |
| "max": 79.4283979833126, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.035636371584171114, | |
| "min": 0.034437064631362514, | |
| "max": 5.9328935937955976, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.1025459234660957, | |
| "min": 2.1025459234660957, | |
| "max": 94.92629750072956, | |
| "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": "1793157262", | |
| "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", | |
| "command_line_arguments": "/content/py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining3 --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": "1793159186" | |
| }, | |
| "total": 1924.4623106170002, | |
| "count": 1, | |
| "self": 0.47969402600028843, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.02052131799973722, | |
| "count": 1, | |
| "self": 0.02052131799973722 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 1923.9620952730002, | |
| "count": 1, | |
| "self": 1.31231807315271, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.220858939000209, | |
| "count": 1, | |
| "self": 2.220858939000209 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 1920.350473231847, | |
| "count": 63450, | |
| "self": 1.4675459777008655, | |
| "children": { | |
| "env_step": { | |
| "total": 1299.0263616570264, | |
| "count": 63450, | |
| "self": 1148.7182835200729, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 149.48574948483383, | |
| "count": 63450, | |
| "self": 4.738627365915818, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 144.747122118918, | |
| "count": 62560, | |
| "self": 144.747122118918 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.8223286521197224, | |
| "count": 63450, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 1920.574419000026, | |
| "count": 63450, | |
| "is_parallel": true, | |
| "self": 876.9746139840972, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0019203540005037212, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006695740012219176, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012507799992818036, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012507799992818036 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05057932200088544, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005483830009325175, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.000444594999862602, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000444594999862602 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04787715400016168, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04787715400016168 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0017091899999286397, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00034534200040070573, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001363847999527934, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001363847999527934 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1043.5998050159287, | |
| "count": 63449, | |
| "is_parallel": true, | |
| "self": 33.14308371779771, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.12850152713054, | |
| "count": 63449, | |
| "is_parallel": true, | |
| "self": 23.12850152713054 | |
| }, | |
| "communicator.exchange": { | |
| "total": 887.0340813509583, | |
| "count": 63449, | |
| "is_parallel": true, | |
| "self": 887.0340813509583 | |
| }, | |
| "steps_from_proto": { | |
| "total": 100.29413842004215, | |
| "count": 63449, | |
| "is_parallel": true, | |
| "self": 20.832797154874243, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 79.4613412651679, | |
| "count": 507592, | |
| "is_parallel": true, | |
| "self": 79.4613412651679 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 619.8565655971197, | |
| "count": 63450, | |
| "self": 2.3601757549440663, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 110.02183654717737, | |
| "count": 63450, | |
| "self": 109.83094536617682, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.19089118100055202, | |
| "count": 2, | |
| "self": 0.19089118100055202 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 507.47455329499826, | |
| "count": 451, | |
| "self": 273.85738955201487, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 233.6171637429834, | |
| "count": 22755, | |
| "self": 233.6171637429834 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.990000424091704e-07, | |
| "count": 1, | |
| "self": 8.990000424091704e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.07844413000020722, | |
| "count": 1, | |
| "self": 0.0010448560005897889, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.07739927399961744, | |
| "count": 1, | |
| "self": 0.07739927399961744 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |