{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1795939803123474, "min": 0.16957439482212067, "max": 1.432275652885437, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5382.072265625, "min": 5092.658203125, "max": 43449.515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999907.0, "min": 29952.0, "max": 2999907.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999907.0, "min": 29952.0, "max": 2999907.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8134300708770752, "min": -0.12626655399799347, "max": 0.8689512014389038, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 252.163330078125, "min": -29.925174713134766, "max": 267.636962890625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004542329348623753, "min": -0.020364167168736458, "max": 0.307184636592865, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4081220626831055, "min": -5.742695331573486, "max": 74.33868408203125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07402727637132298, "min": 0.06433827093135859, "max": 0.07402727637132298, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0363818691985216, "min": 0.48725995429070273, "max": 1.0714805021416396, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014359345837008385, "min": 0.0007453430734880087, "max": 0.01581488397468569, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2010308417181174, "min": 0.009689459955344114, "max": 0.2352929889069249, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4581637996928562e-06, "min": 1.4581637996928562e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0414293195699986e-05, "min": 2.0414293195699986e-05, "max": 0.004011219362926899, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048602142857144, "min": 0.10048602142857144, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068043000000001, "min": 1.3962282666666668, "max": 2.737541433333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.855354071428568e-05, "min": 5.855354071428568e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008197495699999996, "min": 0.0008197495699999996, "max": 0.13371360269, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006311413366347551, "min": 0.006174921523779631, "max": 0.4884788990020752, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0883597880601883, "min": 0.08644890040159225, "max": 3.4193522930145264, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 215.7753623188406, "min": 212.20143884892087, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29777.0, "min": 15984.0, "max": 33776.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7695784086374928, "min": -1.0000000521540642, "max": 1.7859428466430731, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.9713988006115, "min": -29.17080158740282, "max": 250.03199853003025, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7695784086374928, "min": -1.0000000521540642, "max": 1.7859428466430731, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.9713988006115, "min": -29.17080158740282, "max": 250.03199853003025, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014213675673254197, "min": 0.014144838093904712, "max": 9.48478533886373, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9757009185823335, "min": 1.8403398847294739, "max": 151.7565654218197, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749133226", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749140428" }, "total": 7201.5169023729995, "count": 1, "self": 0.5272916849999092, "children": { "run_training.setup": { "total": 0.027964103000158502, "count": 1, "self": 0.027964103000158502 }, "TrainerController.start_learning": { "total": 7200.9616465849995, "count": 1, "self": 3.8900958930862544, "children": { "TrainerController._reset_env": { "total": 2.7461083539999436, "count": 1, "self": 2.7461083539999436 }, "TrainerController.advance": { "total": 7194.238564126912, "count": 194776, "self": 4.2431479919305275, "children": { "env_step": { "total": 5138.481026763071, "count": 194776, "self": 4693.310271749933, "children": { "SubprocessEnvManager._take_step": { "total": 442.8495180089326, "count": 194776, "self": 13.253248360916132, "children": { "TorchPolicy.evaluate": { "total": 429.59626964801646, "count": 187544, "self": 429.59626964801646 } } }, "workers": { "total": 2.3212370042056136, "count": 194776, "self": 0.0, "children": { "worker_root": { "total": 7186.674283379903, "count": 194776, "is_parallel": true, "self": 2823.3359651976725, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001958615999910762, "count": 1, "is_parallel": true, "self": 0.0006379969997851731, "children": { "_process_rank_one_or_two_observation": { "total": 0.001320619000125589, "count": 8, "is_parallel": true, "self": 0.001320619000125589 } } }, "UnityEnvironment.step": { "total": 0.04849513800013483, "count": 1, "is_parallel": true, "self": 0.0005035990000124002, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004446160000952659, "count": 1, "is_parallel": true, "self": 0.0004446160000952659 }, "communicator.exchange": { "total": 0.04599028899997393, "count": 1, "is_parallel": true, "self": 0.04599028899997393 }, "steps_from_proto": { "total": 0.0015566340000532364, "count": 1, "is_parallel": true, "self": 0.0003184340002917452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012381999997614912, "count": 8, "is_parallel": true, "self": 0.0012381999997614912 } } } } } } }, "UnityEnvironment.step": { "total": 4363.33831818223, "count": 194775, "is_parallel": true, "self": 93.37925680023727, "children": { "UnityEnvironment._generate_step_input": { "total": 68.2083151498839, "count": 194775, "is_parallel": true, "self": 68.2083151498839 }, "communicator.exchange": { "total": 3923.6444247589143, "count": 194775, "is_parallel": true, "self": 3923.6444247589143 }, "steps_from_proto": { "total": 278.1063214731944, "count": 194775, "is_parallel": true, "self": 54.62625324045712, "children": { "_process_rank_one_or_two_observation": { "total": 223.48006823273727, "count": 1558200, "is_parallel": true, "self": 223.48006823273727 } } } } } } } } } } }, "trainer_advance": { "total": 2051.51438937191, "count": 194776, "self": 8.104295122880785, "children": { "process_trajectory": { "total": 393.7113804100168, "count": 194776, "self": 393.0427977680156, "children": { "RLTrainer._checkpoint": { "total": 0.6685826420011836, "count": 6, "self": 0.6685826420011836 } } }, "_update_policy": { "total": 1649.6987138390125, "count": 1402, "self": 905.8164828759304, "children": { "TorchPPOOptimizer.update": { "total": 743.8822309630821, "count": 68391, "self": 743.8822309630821 } } } } } } }, "trainer_threads": { "total": 9.880004654405639e-07, "count": 1, "self": 9.880004654405639e-07 }, "TrainerController._save_models": { "total": 0.08687722300055611, "count": 1, "self": 0.0015181750004558126, "children": { "RLTrainer._checkpoint": { "total": 0.0853590480001003, "count": 1, "self": 0.0853590480001003 } } } } } } }