| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.47445669770240784, |
| "min": 0.43982261419296265, |
| "max": 1.403733730316162, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 14408.30078125, |
| "min": 13215.7900390625, |
| "max": 42583.66796875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989874.0, |
| "min": 29951.0, |
| "max": 989874.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989874.0, |
| "min": 29951.0, |
| "max": 989874.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.4006096422672272, |
| "min": -0.11478625237941742, |
| "max": 0.4980531334877014, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 106.56216430664062, |
| "min": -27.66348648071289, |
| "max": 136.96461486816406, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.0054926201701164246, |
| "min": -0.0054926201701164246, |
| "max": 0.36144497990608215, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.4610369205474854, |
| "min": -1.4610369205474854, |
| "max": 85.66246032714844, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06901143105882898, |
| "min": 0.06445328903057436, |
| "max": 0.0740312030217293, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9661600348236058, |
| "min": 0.5182184211521051, |
| "max": 1.0750596806505126, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014816444240218121, |
| "min": 0.00042899518387591286, |
| "max": 0.014816444240218121, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2074302193630537, |
| "min": 0.005147942206510954, |
| "max": 0.21467748933355324, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.247626155585716e-06, |
| "min": 7.247626155585716e-06, |
| "max": 0.00029523295873187143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010146676617820002, |
| "min": 0.00010146676617820002, |
| "max": 0.003507882230706, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10241584285714286, |
| "min": 0.10241584285714286, |
| "max": 0.19841098571428573, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4338218, |
| "min": 1.3888769, |
| "max": 2.5692939999999997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002513427014285715, |
| "min": 0.0002513427014285715, |
| "max": 0.009841257472857143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035187978200000017, |
| "min": 0.0035187978200000017, |
| "max": 0.11695247060000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010743367485702038, |
| "min": 0.010743367485702038, |
| "max": 0.39045676589012146, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.15040715038776398, |
| "min": 0.15040715038776398, |
| "max": 2.7331974506378174, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 455.6818181818182, |
| "min": 371.4078947368421, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30075.0, |
| "min": 16750.0, |
| "max": 32572.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.3624363393720351, |
| "min": -0.9999500517733395, |
| "max": 1.6022631417175657, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 89.92079839855433, |
| "min": -31.998401656746864, |
| "max": 125.55119806528091, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.3624363393720351, |
| "min": -0.9999500517733395, |
| "max": 1.6022631417175657, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 89.92079839855433, |
| "min": -31.998401656746864, |
| "max": 125.55119806528091, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.05056447042399227, |
| "min": 0.04766432330066936, |
| "max": 7.403154622105991, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.33725504798349, |
| "min": 3.33725504798349, |
| "max": 125.85362857580185, |
| "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": "1748142827", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/usr/local/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": "2.7.0+cu126", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1748145092" |
| }, |
| "total": 2265.123587754, |
| "count": 1, |
| "self": 0.5768812350002008, |
| "children": { |
| "run_training.setup": { |
| "total": 0.021342648999961966, |
| "count": 1, |
| "self": 0.021342648999961966 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2264.5253638699996, |
| "count": 1, |
| "self": 1.4526134550114875, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.3748490670000137, |
| "count": 1, |
| "self": 2.3748490670000137 |
| }, |
| "TrainerController.advance": { |
| "total": 2260.611693332987, |
| "count": 63681, |
| "self": 1.6047684570435194, |
| "children": { |
| "env_step": { |
| "total": 1571.2766225709702, |
| "count": 63681, |
| "self": 1411.6310876948205, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 158.8108539160644, |
| "count": 63681, |
| "self": 4.906201400968712, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 153.90465251509568, |
| "count": 62564, |
| "self": 153.90465251509568 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8346809600852794, |
| "count": 63681, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2259.614083560014, |
| "count": 63681, |
| "is_parallel": true, |
| "self": 966.1763791180533, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0023810079997019784, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00076503899981617, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016159689998858084, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016159689998858084 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.049002681000274606, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000566958000035811, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005162070001460961, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005162070001460961 |
| }, |
| "communicator.exchange": { |
| "total": 0.04620117400008894, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04620117400008894 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017183420000037586, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00033101999997597886, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013873220000277797, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013873220000277797 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1293.4377044419607, |
| "count": 63680, |
| "is_parallel": true, |
| "self": 32.72676999589112, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.227008891976766, |
| "count": 63680, |
| "is_parallel": true, |
| "self": 24.227008891976766 |
| }, |
| "communicator.exchange": { |
| "total": 1135.1672762221451, |
| "count": 63680, |
| "is_parallel": true, |
| "self": 1135.1672762221451 |
| }, |
| "steps_from_proto": { |
| "total": 101.3166493319477, |
| "count": 63680, |
| "is_parallel": true, |
| "self": 20.76215605421112, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 80.55449327773658, |
| "count": 509440, |
| "is_parallel": true, |
| "self": 80.55449327773658 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 687.7303023049735, |
| "count": 63681, |
| "self": 2.8137629851412385, |
| "children": { |
| "process_trajectory": { |
| "total": 134.3754070488426, |
| "count": 63681, |
| "self": 134.17207651284207, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20333053600052153, |
| "count": 2, |
| "self": 0.20333053600052153 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 550.5411322709897, |
| "count": 451, |
| "self": 306.69952074897856, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 243.84161152201114, |
| "count": 22788, |
| "self": 243.84161152201114 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0560006558080204e-06, |
| "count": 1, |
| "self": 1.0560006558080204e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08620695900026476, |
| "count": 1, |
| "self": 0.0012561580006149597, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0849508009996498, |
| "count": 1, |
| "self": 0.0849508009996498 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
