{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44520634412765503, "min": 0.44520634412765503, "max": 1.3810703754425049, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13477.2861328125, "min": 13477.2861328125, "max": 41896.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43212783336639404, "min": -0.18313734233379364, "max": 0.4684053063392639, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.24238586425781, "min": -43.40354919433594, "max": 126.00102996826172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.45579254627227783, "min": -0.014988468959927559, "max": 0.5163129568099976, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 122.60819244384766, "min": -3.8070712089538574, "max": 122.60819244384766, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06715057970787812, "min": 0.06397525224795876, "max": 0.07444999086032576, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0072586956181717, "min": 0.5205023378420965, "max": 1.0422998720445606, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.026387546092478772, "min": 0.00014067862458904144, "max": 0.027181496368496125, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3958131913871816, "min": 0.0018288221196575388, "max": 0.3958131913871816, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.553237482286666e-06, "min": 7.553237482286666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011329856223429998, "min": 0.00011329856223429998, "max": 0.0035073944308686, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251771333333336, "min": 0.10251771333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377657000000005, "min": 1.3886848, "max": 2.5691314000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261519562, "min": 0.000261519562, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00392279343, "min": 0.00392279343, "max": 0.11693622685999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01139814779162407, "min": 0.011248939670622349, "max": 0.536886990070343, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17097221314907074, "min": 0.15748515725135803, "max": 3.758208751678467, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 407.8904109589041, "min": 407.8904109589041, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29776.0, "min": 15984.0, "max": 33297.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5098931326033318, "min": -1.0000000521540642, "max": 1.5100130878511022, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 110.22219868004322, "min": -31.996001675724983, "max": 110.22219868004322, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5098931326033318, "min": -1.0000000521540642, "max": 1.5100130878511022, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 110.22219868004322, "min": -31.996001675724983, "max": 110.22219868004322, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04831758370600666, "min": 0.04831758370600666, "max": 10.49727188050747, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5271836105384864, "min": 3.319309462356614, "max": 167.9563500881195, "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": "1756736032", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756739191" }, "total": 3159.483036627, "count": 1, "self": 0.784690239000156, "children": { "run_training.setup": { "total": 0.03539846199987551, "count": 1, "self": 0.03539846199987551 }, "TrainerController.start_learning": { "total": 3158.662947926, "count": 1, "self": 2.2049312730096062, "children": { "TrainerController._reset_env": { "total": 2.5674827580000965, "count": 1, "self": 2.5674827580000965 }, "TrainerController.advance": { "total": 3153.812066394991, "count": 63622, "self": 2.3488012889456513, "children": { "env_step": { "total": 2082.12002715005, "count": 63622, "self": 1921.229188267994, "children": { "SubprocessEnvManager._take_step": { "total": 159.55175991598435, "count": 63622, "self": 7.067049272874328, "children": { "TorchPolicy.evaluate": { "total": 152.48471064311002, "count": 62559, "self": 152.48471064311002 } } }, "workers": { "total": 1.3390789660718383, "count": 63622, "self": 0.0, "children": { "worker_root": { "total": 3149.884490215956, "count": 63622, "is_parallel": true, "self": 1405.922514306957, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032762359999196633, "count": 1, "is_parallel": true, "self": 0.0012652909997541428, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020109450001655205, "count": 8, "is_parallel": true, "self": 0.0020109450001655205 } } }, "UnityEnvironment.step": { "total": 0.06552208800007975, "count": 1, "is_parallel": true, "self": 0.0007371579999926325, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005448760000490438, "count": 1, "is_parallel": true, "self": 0.0005448760000490438 }, "communicator.exchange": { "total": 0.062124616999881255, "count": 1, "is_parallel": true, "self": 0.062124616999881255 }, "steps_from_proto": { "total": 0.002115437000156817, "count": 1, "is_parallel": true, "self": 0.00047439400032089907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016410429998359177, "count": 8, "is_parallel": true, "self": 0.0016410429998359177 } } } } } } }, "UnityEnvironment.step": { "total": 1743.9619759089987, "count": 63621, "is_parallel": true, "self": 44.466937608948456, "children": { "UnityEnvironment._generate_step_input": { "total": 30.986048664010468, "count": 63621, "is_parallel": true, "self": 30.986048664010468 }, "communicator.exchange": { "total": 1541.1463884331004, "count": 63621, "is_parallel": true, "self": 1541.1463884331004 }, "steps_from_proto": { "total": 127.36260120293946, "count": 63621, "is_parallel": true, "self": 27.454550153152695, "children": { "_process_rank_one_or_two_observation": { "total": 99.90805104978676, "count": 508968, "is_parallel": true, "self": 99.90805104978676 } } } } } } } } } } }, "trainer_advance": { "total": 1069.343237955995, "count": 63622, "self": 4.333086090933648, "children": { "process_trajectory": { "total": 159.40494199206137, "count": 63622, "self": 159.2158299930618, "children": { "RLTrainer._checkpoint": { "total": 0.18911199899957865, "count": 2, "self": 0.18911199899957865 } } }, "_update_policy": { "total": 905.6052098729999, "count": 452, "self": 356.510550168922, "children": { "TorchPPOOptimizer.update": { "total": 549.0946597040779, "count": 22749, "self": 549.0946597040779 } } } } } } }, "trainer_threads": { "total": 9.779996616998687e-07, "count": 1, "self": 9.779996616998687e-07 }, "TrainerController._save_models": { "total": 0.07846652199987147, "count": 1, "self": 0.0019340090002515353, "children": { "RLTrainer._checkpoint": { "total": 0.07653251299961994, "count": 1, "self": 0.07653251299961994 } } } } } } }