{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37082338333129883, "min": 0.37082338333129883, "max": 1.450534701347351, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11059.4365234375, "min": 11059.4365234375, "max": 44003.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46717536449432373, "min": -0.09909094870090485, "max": 0.46717536449432373, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.80146789550781, "min": -23.826923370361328, "max": 124.35867309570312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01598644256591797, "min": -0.0016831925604492426, "max": 0.2763209342956543, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.236407279968262, "min": -0.4443628489971161, "max": 66.86966705322266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06693687420573995, "min": 0.06464208214875478, "max": 0.07423398879788509, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9371162388803592, "min": 0.5196379215851956, "max": 1.0339429914602078, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014175034934028408, "min": 0.00011465585531397217, "max": 0.01578206924571351, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1984504890763977, "min": 0.0014905261190816383, "max": 0.22094896943998915, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.684833152707142e-06, "min": 7.684833152707142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010758766413789999, "min": 0.00010758766413789999, "max": 0.003757464147512, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256157857142857, "min": 0.10256157857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358621, "min": 1.3886848, "max": 2.6524880000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002659016992857144, "min": 0.0002659016992857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037226237900000016, "min": 0.0037226237900000016, "max": 0.12526355120000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011552269570529461, "min": 0.011552269570529461, "max": 0.42442578077316284, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1617317795753479, "min": 0.1617317795753479, "max": 2.970980405807495, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 408.28125, "min": 389.144578313253, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26130.0, "min": 15984.0, "max": 33614.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3979630580315223, "min": -1.0000000521540642, "max": 1.5385397358472088, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.86759877204895, "min": -30.992001585662365, "max": 127.69879807531834, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3979630580315223, "min": -1.0000000521540642, "max": 1.5385397358472088, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.86759877204895, "min": -30.992001585662365, "max": 127.69879807531834, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.050280268298676954, "min": 0.050280268298676954, "max": 8.255877086892724, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.268217439414002, "min": 3.268217439414002, "max": 132.09403339028358, "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": "1710377585", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710380672" }, "total": 3087.2467811099996, "count": 1, "self": 0.630843664999702, "children": { "run_training.setup": { "total": 0.06449297599988313, "count": 1, "self": 0.06449297599988313 }, "TrainerController.start_learning": { "total": 3086.5514444689998, "count": 1, "self": 2.201955552929576, "children": { "TrainerController._reset_env": { "total": 2.638008210999942, "count": 1, "self": 2.638008210999942 }, "TrainerController.advance": { "total": 3081.62128009107, "count": 63727, "self": 2.352056937051657, "children": { "env_step": { "total": 2041.9549021379974, "count": 63727, "self": 1882.1491769709637, "children": { "SubprocessEnvManager._take_step": { "total": 158.4561099849975, "count": 63727, "self": 6.383160740994754, "children": { "TorchPolicy.evaluate": { "total": 152.07294924400276, "count": 62566, "self": 152.07294924400276 } } }, "workers": { "total": 1.349615182036132, "count": 63727, "self": 0.0, "children": { "worker_root": { "total": 3080.8796378029615, "count": 63727, "is_parallel": true, "self": 1370.6714190769956, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002943217999927583, "count": 1, "is_parallel": true, "self": 0.0008950199996888841, "children": { "_process_rank_one_or_two_observation": { "total": 0.002048198000238699, "count": 8, "is_parallel": true, "self": 0.002048198000238699 } } }, "UnityEnvironment.step": { "total": 0.06126215799986312, "count": 1, "is_parallel": true, "self": 0.0007394860001568304, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005078919998595666, "count": 1, "is_parallel": true, "self": 0.0005078919998595666 }, "communicator.exchange": { "total": 0.05794540400006554, "count": 1, "is_parallel": true, "self": 0.05794540400006554 }, "steps_from_proto": { "total": 0.0020693759997811867, "count": 1, "is_parallel": true, "self": 0.0004481239998312958, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016212519999498909, "count": 8, "is_parallel": true, "self": 0.0016212519999498909 } } } } } } }, "UnityEnvironment.step": { "total": 1710.208218725966, "count": 63726, "is_parallel": true, "self": 47.0196320120408, "children": { "UnityEnvironment._generate_step_input": { "total": 26.11465551598144, "count": 63726, "is_parallel": true, "self": 26.11465551598144 }, "communicator.exchange": { "total": 1510.9201699689963, "count": 63726, "is_parallel": true, "self": 1510.9201699689963 }, "steps_from_proto": { "total": 126.15376122894736, "count": 63726, "is_parallel": true, "self": 26.803386564085486, "children": { "_process_rank_one_or_two_observation": { "total": 99.35037466486187, "count": 509808, "is_parallel": true, "self": 99.35037466486187 } } } } } } } } } } }, "trainer_advance": { "total": 1037.3143210160208, "count": 63727, "self": 4.630696583051304, "children": { "process_trajectory": { "total": 156.53040870896393, "count": 63727, "self": 156.34742579196427, "children": { "RLTrainer._checkpoint": { "total": 0.18298291699966285, "count": 2, "self": 0.18298291699966285 } } }, "_update_policy": { "total": 876.1532157240056, "count": 454, "self": 351.5960481860245, "children": { "TorchPPOOptimizer.update": { "total": 524.5571675379811, "count": 22788, "self": 524.5571675379811 } } } } } } }, "trainer_threads": { "total": 9.7599968285067e-07, "count": 1, "self": 9.7599968285067e-07 }, "TrainerController._save_models": { "total": 0.09019963800074038, "count": 1, "self": 0.004032350000670704, "children": { "RLTrainer._checkpoint": { "total": 0.08616728800006968, "count": 1, "self": 0.08616728800006968 } } } } } } }