{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7786479592323303, "min": 0.7688250541687012, "max": 1.4515422582626343, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 23234.85546875, "min": 23163.162109375, "max": 44033.984375, "count": 16 }, "Pyramids.Step.mean": { "value": 479952.0, "min": 29952.0, "max": 479952.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479952.0, "min": 29952.0, "max": 479952.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0510147400200367, "min": -0.1008923202753067, "max": -0.03205851837992668, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -12.396581649780273, "min": -24.41594123840332, "max": -7.758161544799805, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015433819964528084, "min": 0.00985634233802557, "max": 0.5359538793563843, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.750418186187744, "min": 2.385234832763672, "max": 127.02106475830078, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06560667988184257, "min": 0.06560667988184257, "max": 0.07155880220785825, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9184935183457961, "min": 0.4808249265867441, "max": 0.978930355920312, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0028387685356078265, "min": 0.0004598248235613958, "max": 0.01305302486250374, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03974275949850957, "min": 0.005058073059175354, "max": 0.09137117403752618, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1486607123542853e-05, "min": 2.1486607123542853e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00030081249972959995, "min": 0.00030081249972959995, "max": 0.0028504802498399997, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10716217142857143, "min": 0.10716217142857143, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5002704, "min": 1.3773696000000002, "max": 2.1742757999999998, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007255009257142857, "min": 0.0007255009257142857, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.01015701296, "min": 0.01015701296, "max": 0.095040984, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016022218391299248, "min": 0.016022218391299248, "max": 0.3712592124938965, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22431105375289917, "min": 0.22431105375289917, "max": 2.5988144874572754, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 933.8235294117648, "min": 899.4848484848485, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31750.0, "min": 15984.0, "max": 32894.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5226471082252615, "min": -1.0000000521540642, "max": -0.4826118130894268, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.77000167965889, "min": -31.998001664876938, "max": -15.426801197230816, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5226471082252615, "min": -1.0000000521540642, "max": -0.4826118130894268, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.77000167965889, "min": -31.998001664876938, "max": -15.426801197230816, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1553061647915884, "min": 0.1553061647915884, "max": 8.130234810523689, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 5.2804096029140055, "min": 4.678207612130791, "max": 130.08375696837902, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690531274", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690532326" }, "total": 1051.378972977, "count": 1, "self": 0.47623588400028893, "children": { "run_training.setup": { "total": 0.0351300209999863, "count": 1, "self": 0.0351300209999863 }, "TrainerController.start_learning": { "total": 1050.8676070719998, "count": 1, "self": 0.7188658179675258, "children": { "TrainerController._reset_env": { "total": 4.746945421999953, "count": 1, "self": 4.746945421999953 }, "TrainerController.advance": { "total": 1045.3010491000323, "count": 31500, "self": 0.7169794180263125, "children": { "env_step": { "total": 721.8524109820146, "count": 31500, "self": 665.1240610329833, "children": { "SubprocessEnvManager._take_step": { "total": 56.30349620200013, "count": 31500, "self": 2.448878831962702, "children": { "TorchPolicy.evaluate": { "total": 53.85461737003743, "count": 31319, "self": 53.85461737003743 } } }, "workers": { "total": 0.42485374703119305, "count": 31500, "self": 0.0, "children": { "worker_root": { "total": 1048.3197353870714, "count": 31500, "is_parallel": true, "self": 441.68564853411044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001809629000035784, "count": 1, "is_parallel": true, "self": 0.0005500430002030043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012595859998327796, "count": 8, "is_parallel": true, "self": 0.0012595859998327796 } } }, "UnityEnvironment.step": { "total": 0.09708606899994265, "count": 1, "is_parallel": true, "self": 0.0005453789995044644, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005535250002139946, "count": 1, "is_parallel": true, "self": 0.0005535250002139946 }, "communicator.exchange": { "total": 0.09404816500000379, "count": 1, "is_parallel": true, "self": 0.09404816500000379 }, "steps_from_proto": { "total": 0.0019390000002204033, "count": 1, "is_parallel": true, "self": 0.0003796279997914098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015593720004289935, "count": 8, "is_parallel": true, "self": 0.0015593720004289935 } } } } } } }, "UnityEnvironment.step": { "total": 606.634086852961, "count": 31499, "is_parallel": true, "self": 17.237914071940395, "children": { "UnityEnvironment._generate_step_input": { "total": 11.740815574991302, "count": 31499, "is_parallel": true, "self": 11.740815574991302 }, "communicator.exchange": { "total": 525.7045810929612, "count": 31499, "is_parallel": true, "self": 525.7045810929612 }, "steps_from_proto": { "total": 51.95077611306806, "count": 31499, "is_parallel": true, "self": 10.538247929070167, "children": { "_process_rank_one_or_two_observation": { "total": 41.41252818399789, "count": 251992, "is_parallel": true, "self": 41.41252818399789 } } } } } } } } } } }, "trainer_advance": { "total": 322.7316586999914, "count": 31500, "self": 1.1145481400058088, "children": { "process_trajectory": { "total": 53.495999761989424, "count": 31500, "self": 53.34063134398957, "children": { "RLTrainer._checkpoint": { "total": 0.15536841799985268, "count": 1, "self": 0.15536841799985268 } } }, "_update_policy": { "total": 268.12111079799615, "count": 207, "self": 173.86927859399384, "children": { "TorchPPOOptimizer.update": { "total": 94.25183220400231, "count": 11436, "self": 94.25183220400231 } } } } } } }, "trainer_threads": { "total": 8.590000106778461e-07, "count": 1, "self": 8.590000106778461e-07 }, "TrainerController._save_models": { "total": 0.10074587300005078, "count": 1, "self": 0.001389394999932847, "children": { "RLTrainer._checkpoint": { "total": 0.09935647800011793, "count": 1, "self": 0.09935647800011793 } } } } } } }