{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6644560098648071, "min": 0.6553872227668762, "max": 1.4159610271453857, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19986.8359375, "min": 19577.7265625, "max": 42954.59375, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29922.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29922.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18590296804904938, "min": -0.09537482261657715, "max": 0.25536054372787476, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 46.661643981933594, "min": -22.985332489013672, "max": 65.37229919433594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012728250585496426, "min": -0.011845201253890991, "max": 0.4420885741710663, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.194790840148926, "min": -3.0323715209960938, "max": 104.77499389648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07100858917900561, "min": 0.06372149635740278, "max": 0.07289612482703636, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9941202485060785, "min": 0.48569041460380497, "max": 1.0764858158123818, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010156901970601342, "min": 0.0004417927547434617, "max": 0.012413233161421436, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14219662758841878, "min": 0.006185098566408464, "max": 0.16553266657708673, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.533118917564288e-06, "min": 7.533118917564288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010546366484590003, "min": 0.00010546366484590003, "max": 0.0035070824309725995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251100714285714, "min": 0.10251100714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351541, "min": 1.3886848, "max": 2.5690274000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026084961357142865, "min": 0.00026084961357142865, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003651894590000001, "min": 0.003651894590000001, "max": 0.11692583725999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009773164056241512, "min": 0.009773164056241512, "max": 0.5140397548675537, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13682429492473602, "min": 0.13682429492473602, "max": 3.598278284072876, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 632.7173913043479, "min": 574.265306122449, "max": 991.8064516129032, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29105.0, "min": 16849.0, "max": 32734.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7583695390950078, "min": -0.9315697464979056, "max": 1.0186489431225523, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 34.88499879837036, "min": -30.741801634430885, "max": 49.913798213005066, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7583695390950078, "min": -0.9315697464979056, "max": 1.0186489431225523, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 34.88499879837036, "min": -30.741801634430885, "max": 49.913798213005066, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06464987815074298, "min": 0.06464987815074298, "max": 10.413028252475401, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9738943949341774, "min": 2.9738943949341774, "max": 177.02148029208183, "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": "1687569078", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1687571119" }, "total": 2041.038591602, "count": 1, "self": 0.6886604019998686, "children": { "run_training.setup": { "total": 0.0373283450001054, "count": 1, "self": 0.0373283450001054 }, "TrainerController.start_learning": { "total": 2040.312602855, "count": 1, "self": 1.246511543051156, "children": { "TrainerController._reset_env": { "total": 4.816836362000004, "count": 1, "self": 4.816836362000004 }, "TrainerController.advance": { "total": 2034.1048558889488, "count": 63316, "self": 1.278946867987088, "children": { "env_step": { "total": 1409.889250547021, "count": 63316, "self": 1305.179602299199, "children": { "SubprocessEnvManager._take_step": { "total": 103.96564977192588, "count": 63316, "self": 4.551662451894572, "children": { "TorchPolicy.evaluate": { "total": 99.41398732003131, "count": 62560, "self": 99.41398732003131 } } }, "workers": { "total": 0.7439984758962055, "count": 63316, "self": 0.0, "children": { "worker_root": { "total": 2035.548964012955, "count": 63316, "is_parallel": true, "self": 836.9221318180005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001763124000035532, "count": 1, "is_parallel": true, "self": 0.0005280519999359967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012350720000995352, "count": 8, "is_parallel": true, "self": 0.0012350720000995352 } } }, "UnityEnvironment.step": { "total": 0.10209290000011606, "count": 1, "is_parallel": true, "self": 0.0005431410002074699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048818699997355, "count": 1, "is_parallel": true, "self": 0.00048818699997355 }, "communicator.exchange": { "total": 0.09911876899991512, "count": 1, "is_parallel": true, "self": 0.09911876899991512 }, "steps_from_proto": { "total": 0.0019428030000199215, "count": 1, "is_parallel": true, "self": 0.00043077099985566747, "children": { "_process_rank_one_or_two_observation": { "total": 0.001512032000164254, "count": 8, "is_parallel": true, "self": 0.001512032000164254 } } } } } } }, "UnityEnvironment.step": { "total": 1198.6268321949544, "count": 63315, "is_parallel": true, "self": 32.126712837926334, "children": { "UnityEnvironment._generate_step_input": { "total": 22.413750842967374, "count": 63315, "is_parallel": true, "self": 22.413750842967374 }, "communicator.exchange": { "total": 1046.890697393037, "count": 63315, "is_parallel": true, "self": 1046.890697393037 }, "steps_from_proto": { "total": 97.19567112102368, "count": 63315, "is_parallel": true, "self": 18.74910887230999, "children": { "_process_rank_one_or_two_observation": { "total": 78.44656224871369, "count": 506520, "is_parallel": true, "self": 78.44656224871369 } } } } } } } } } } }, "trainer_advance": { "total": 622.9366584739407, "count": 63316, "self": 2.364941834956653, "children": { "process_trajectory": { "total": 104.99480809298416, "count": 63316, "self": 104.73952101398413, "children": { "RLTrainer._checkpoint": { "total": 0.255287079000027, "count": 2, "self": 0.255287079000027 } } }, "_update_policy": { "total": 515.5769085459999, "count": 450, "self": 330.684461386021, "children": { "TorchPPOOptimizer.update": { "total": 184.89244715997893, "count": 22797, "self": 184.89244715997893 } } } } } } }, "trainer_threads": { "total": 1.2810000953322742e-06, "count": 1, "self": 1.2810000953322742e-06 }, "TrainerController._save_models": { "total": 0.14439777999996295, "count": 1, "self": 0.0019448539997029002, "children": { "RLTrainer._checkpoint": { "total": 0.14245292600026005, "count": 1, "self": 0.14245292600026005 } } } } } } }