| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.292867511510849, |
| "min": 0.292867511510849, |
| "max": 1.4642465114593506, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8865.685546875, |
| "min": 8805.5087890625, |
| "max": 44419.3828125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989910.0, |
| "min": 29952.0, |
| "max": 989910.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989910.0, |
| "min": 29952.0, |
| "max": 989910.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6543437242507935, |
| "min": -0.08927173167467117, |
| "max": 0.7030113339424133, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 188.45098876953125, |
| "min": -21.514488220214844, |
| "max": 203.873291015625, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.05774553120136261, |
| "min": -0.07649531960487366, |
| "max": 0.2338489145040512, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -16.630712509155273, |
| "min": -21.036212921142578, |
| "max": 56.123741149902344, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06837654580530297, |
| "min": 0.0651880816523967, |
| "max": 0.07314440402180858, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0256481870795446, |
| "min": 0.47240345436742137, |
| "max": 1.0891147978351605, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01677849803624364, |
| "min": 0.0004900508075834577, |
| "max": 0.01744969825224308, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2516774705436546, |
| "min": 0.00637066049858495, |
| "max": 0.2516774705436546, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.430337523253336e-06, |
| "min": 7.430337523253336e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011145506284880004, |
| "min": 0.00011145506284880004, |
| "max": 0.0037587640470786994, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10247674666666667, |
| "min": 0.10247674666666667, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5371512, |
| "min": 1.3691136000000002, |
| "max": 2.6529212999999996, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025742699200000005, |
| "min": 0.00025742699200000005, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003861404880000001, |
| "min": 0.003861404880000001, |
| "max": 0.12530683787, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.011435522697865963, |
| "min": 0.011435522697865963, |
| "max": 0.340349942445755, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.17153283953666687, |
| "min": 0.1612253338098526, |
| "max": 2.3824496269226074, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 296.5742574257426, |
| "min": 282.67619047619047, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29954.0, |
| "min": 15984.0, |
| "max": 32272.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6856117548019278, |
| "min": -1.0000000521540642, |
| "max": 1.7156922973405857, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 171.93239898979664, |
| "min": -32.000001668930054, |
| "max": 179.1541986465454, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6856117548019278, |
| "min": -1.0000000521540642, |
| "max": 1.7156922973405857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 171.93239898979664, |
| "min": -32.000001668930054, |
| "max": 179.1541986465454, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.035000291836873726, |
| "min": 0.03352028891864533, |
| "max": 6.797358280047774, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.5700297673611203, |
| "min": 3.486110047539114, |
| "max": 108.75773248076439, |
| "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": "1744333317", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/ubuntu/miniconda3/envs/mltrain2/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1744335787" |
| }, |
| "total": 2470.366532942, |
| "count": 1, |
| "self": 0.42409720699833997, |
| "children": { |
| "run_training.setup": { |
| "total": 0.017949369001144078, |
| "count": 1, |
| "self": 0.017949369001144078 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2469.9244863660006, |
| "count": 1, |
| "self": 0.8482627828761906, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.624437456999658, |
| "count": 1, |
| "self": 1.624437456999658 |
| }, |
| "TrainerController.advance": { |
| "total": 2467.401466086125, |
| "count": 64001, |
| "self": 0.8482488874105911, |
| "children": { |
| "env_step": { |
| "total": 2004.417555771006, |
| "count": 64001, |
| "self": 1915.9608666511594, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 87.93474847890138, |
| "count": 64001, |
| "self": 3.200597955015837, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 84.73415052388555, |
| "count": 62560, |
| "self": 84.73415052388555 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.521940640945104, |
| "count": 64001, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2465.291478340643, |
| "count": 64001, |
| "is_parallel": true, |
| "self": 669.6496382317564, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.00584009399972274, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0019165509984304663, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.003923543001292273, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.003923543001292273 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05997924299845181, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008235669956775382, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0007882080008130288, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007882080008130288 |
| }, |
| "communicator.exchange": { |
| "total": 0.05554212400056713, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05554212400056713 |
| }, |
| "steps_from_proto": { |
| "total": 0.0028253440013941145, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008181010070984485, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002007242994295666, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002007242994295666 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1795.6418401088868, |
| "count": 64000, |
| "is_parallel": true, |
| "self": 50.50559937539583, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 37.20690114487297, |
| "count": 64000, |
| "is_parallel": true, |
| "self": 37.20690114487297 |
| }, |
| "communicator.exchange": { |
| "total": 1559.478597225927, |
| "count": 64000, |
| "is_parallel": true, |
| "self": 1559.478597225927 |
| }, |
| "steps_from_proto": { |
| "total": 148.45074236269102, |
| "count": 64000, |
| "is_parallel": true, |
| "self": 31.607134842186497, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 116.84360752050452, |
| "count": 512000, |
| "is_parallel": true, |
| "self": 116.84360752050452 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 462.1356614277083, |
| "count": 64001, |
| "self": 1.7323536554504244, |
| "children": { |
| "process_trajectory": { |
| "total": 87.54956158526147, |
| "count": 64001, |
| "self": 87.4136778932625, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13588369199896988, |
| "count": 2, |
| "self": 0.13588369199896988 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 372.85374618699643, |
| "count": 448, |
| "self": 183.12447939516824, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 189.7292667918282, |
| "count": 22770, |
| "self": 189.7292667918282 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.040005923248827e-07, |
| "count": 1, |
| "self": 8.040005923248827e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.05031923599926813, |
| "count": 1, |
| "self": 0.0010393539996584877, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.04927988199960964, |
| "count": 1, |
| "self": 0.04927988199960964 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
