{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7177714705467224, "min": 0.7067081332206726, "max": 1.6063541173934937, "count": 300 }, "Pyramids.Policy.Entropy.sum": { "value": 6867.6376953125, "min": 6671.32470703125, "max": 19738.87890625, "count": 300 }, "Pyramids.Step.mean": { "value": 2999870.0, "min": 9984.0, "max": 2999870.0, "count": 300 }, "Pyramids.Step.sum": { "value": 2999870.0, "min": 9984.0, "max": 2999870.0, "count": 300 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09788888692855835, "min": -0.10054291784763336, "max": 0.07294552028179169, "count": 300 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -3.915555477142334, "min": -4.114132404327393, "max": 2.8448753356933594, "count": 300 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.05017721684416756, "min": 0.041116138609192734, "max": 0.06592731363007574, "count": 300 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.10035443368833512, "min": 0.0441928361675569, "max": 0.13185462726015149, "count": 300 }, "Pyramids.Losses.ValueLoss.mean": { "value": 8.133076136118689e-06, "min": 1.3738508204638063e-09, "max": 0.005506745152524672, "count": 300 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.6266152272237377e-05, "min": 1.3738508204638063e-09, "max": 0.008693760226672316, "count": 300 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.79766470733323e-07, "min": 9.79766470733323e-07, "max": 0.0004986346669397332, "count": 300 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.959532941466646e-06, "min": 1.959532941466646e-06, "max": 0.0009853013362730667, "count": 300 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10009796666666668, "min": 0.10009796666666668, "max": 0.1498634666666667, "count": 300 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.20019593333333335, "min": 0.10140496666666665, "max": 0.29853013333333334, "count": 300 }, "Pyramids.Policy.Beta.mean": { "value": 2.9573739999999797e-05, "min": 2.9573739999999797e-05, "max": 0.00997272064, "count": 300 }, "Pyramids.Policy.Beta.sum": { "value": 5.9147479999999595e-05, "min": 5.9147479999999595e-05, "max": 0.019706320639999997, "count": 300 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 300 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 776.5, "max": 999.0, "count": 265 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 1998.0, "min": 973.0, "max": 15984.0, "count": 265 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999556144078573, "min": -1.0000000596046448, "max": 0.22339993715286255, "count": 284 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.999600529670715, "min": -16.000000953674316, "max": 0.4467998743057251, "count": 284 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999556144078573, "min": -1.0000000596046448, "max": 0.22339993715286255, "count": 284 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.999600529670715, "min": -16.000000953674316, "max": 0.4467998743057251, "count": 284 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739320653", "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-v2 --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": "1739325980" }, "total": 5326.623036740999, "count": 1, "self": 0.48645957999815437, "children": { "run_training.setup": { "total": 0.020566655000038736, "count": 1, "self": 0.020566655000038736 }, "TrainerController.start_learning": { "total": 5326.116010506001, "count": 1, "self": 3.4860972659862455, "children": { "TrainerController._reset_env": { "total": 2.1075093660001585, "count": 1, "self": 2.1075093660001585 }, "TrainerController.advance": { "total": 5320.373425120013, "count": 187833, "self": 3.8027407903528, "children": { "env_step": { "total": 3449.811039562912, "count": 187833, "self": 2886.749910251785, "children": { "SubprocessEnvManager._take_step": { "total": 560.8786265946956, "count": 187833, "self": 13.64933403514442, "children": { "TorchPolicy.evaluate": { "total": 547.2292925595511, "count": 187598, "self": 547.2292925595511 } } }, "workers": { "total": 2.1825027164313724, "count": 187833, "self": 0.0, "children": { "worker_root": { "total": 5313.446109011701, "count": 187833, "is_parallel": true, "self": 2734.105127706449, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00214386699917668, "count": 1, "is_parallel": true, "self": 0.0007049929990898818, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014388740000867983, "count": 8, "is_parallel": true, "self": 0.0014388740000867983 } } }, "UnityEnvironment.step": { "total": 0.047453265000513056, "count": 1, "is_parallel": true, "self": 0.000512234000780154, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005919180002820212, "count": 1, "is_parallel": true, "self": 0.0005919180002820212 }, "communicator.exchange": { "total": 0.04478020899932744, "count": 1, "is_parallel": true, "self": 0.04478020899932744 }, "steps_from_proto": { "total": 0.0015689040001234389, "count": 1, "is_parallel": true, "self": 0.0003217389985366026, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012471650015868363, "count": 8, "is_parallel": true, "self": 0.0012471650015868363 } } } } } } }, "UnityEnvironment.step": { "total": 2579.340981305252, "count": 187832, "is_parallel": true, "self": 92.92574664181575, "children": { "UnityEnvironment._generate_step_input": { "total": 67.53816712221942, "count": 187832, "is_parallel": true, "self": 67.53816712221942 }, "communicator.exchange": { "total": 2136.7579698530153, "count": 187832, "is_parallel": true, "self": 2136.7579698530153 }, "steps_from_proto": { "total": 282.1190976882017, "count": 187832, "is_parallel": true, "self": 55.25429518263263, "children": { "_process_rank_one_or_two_observation": { "total": 226.86480250556906, "count": 1502656, "is_parallel": true, "self": 226.86480250556906 } } } } } } } } } } }, "trainer_advance": { "total": 1866.7596447667484, "count": 187833, "self": 4.963727663816826, "children": { "process_trajectory": { "total": 315.9948084179432, "count": 187833, "self": 306.31589488594545, "children": { "RLTrainer._checkpoint": { "total": 9.67891353199775, "count": 60, "self": 9.67891353199775 } } }, "_update_policy": { "total": 1545.8011086849883, "count": 494, "self": 856.5078692949955, "children": { "TorchPPOOptimizer.update": { "total": 689.2932393899928, "count": 57135, "self": 689.2932393899928 } } } } } } }, "trainer_threads": { "total": 8.469996828353032e-07, "count": 1, "self": 8.469996828353032e-07 }, "TrainerController._save_models": { "total": 0.1489779070016084, "count": 1, "self": 0.002215407002950087, "children": { "RLTrainer._checkpoint": { "total": 0.1467624999986583, "count": 1, "self": 0.1467624999986583 } } } } } } }