{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7254295349121094, "min": 0.7174833416938782, "max": 1.4814491271972656, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22203.947265625, "min": 21454.53125, "max": 44941.2421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3666561245918274, "min": -0.07990157604217529, "max": 0.3666561245918274, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.3305892944336, "min": -19.41608238220215, "max": 95.3305892944336, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.13634075224399567, "min": -0.13634075224399567, "max": 0.2578839361667633, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -35.4485969543457, "min": -35.4485969543457, "max": 61.11849594116211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06670238321177228, "min": 0.06568921977671709, "max": 0.07465125733192665, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.933833364964812, "min": 0.5225588013234865, "max": 1.0572146726424085, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017249061233347414, "min": 0.0009127083302220212, "max": 0.017249061233347414, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24148685726686378, "min": 0.010952499962664255, "max": 0.24148685726686378, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.7379974207e-06, "min": 7.7379974207e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010833196388980001, "min": 0.00010833196388980001, "max": 0.0035075873308042993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025793, "min": 0.1025793, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361102, "min": 1.3886848, "max": 2.5691957000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026767207000000004, "min": 0.00026767207000000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037474089800000007, "min": 0.0037474089800000007, "max": 0.11694265042999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008044392801821232, "min": 0.007822993211448193, "max": 0.35751107335090637, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1126215010881424, "min": 0.10952191054821014, "max": 2.502577543258667, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 487.13235294117646, "min": 470.7704918032787, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33125.0, "min": 15984.0, "max": 33125.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.248070563244469, "min": -1.0000000521540642, "max": 1.3324360396774089, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.8687983006239, "min": -30.298401668667793, "max": 84.8687983006239, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.248070563244469, "min": -1.0000000521540642, "max": 1.3324360396774089, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.8687983006239, "min": -30.298401668667793, "max": 84.8687983006239, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04076498810900375, "min": 0.038301385930056116, "max": 6.807073215954006, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.772019191412255, "min": 2.3363845417334232, "max": 108.91317145526409, "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": "1746360972", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746363885" }, "total": 2913.3210144679997, "count": 1, "self": 1.052021866999894, "children": { "run_training.setup": { "total": 0.031279519000008804, "count": 1, "self": 0.031279519000008804 }, "TrainerController.start_learning": { "total": 2912.2377130819996, "count": 1, "self": 2.361884033935894, "children": { "TrainerController._reset_env": { "total": 2.6877357159999065, "count": 1, "self": 2.6877357159999065 }, "TrainerController.advance": { "total": 2907.0694845270637, "count": 63534, "self": 2.6417727821717563, "children": { "env_step": { "total": 1853.7283125739316, "count": 63534, "self": 1695.3079959429208, "children": { "SubprocessEnvManager._take_step": { "total": 157.0703764549662, "count": 63534, "self": 6.8046473690715175, "children": { "TorchPolicy.evaluate": { "total": 150.2657290858947, "count": 62562, "self": 150.2657290858947 } } }, "workers": { "total": 1.3499401760445835, "count": 63534, "self": 0.0, "children": { "worker_root": { "total": 2905.4466638220215, "count": 63534, "is_parallel": true, "self": 1374.0886987720023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029624360001889727, "count": 1, "is_parallel": true, "self": 0.0010265770001751662, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019358590000138065, "count": 8, "is_parallel": true, "self": 0.0019358590000138065 } } }, "UnityEnvironment.step": { "total": 0.060274848000062775, "count": 1, "is_parallel": true, "self": 0.0006809160001921555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005408449999322329, "count": 1, "is_parallel": true, "self": 0.0005408449999322329 }, "communicator.exchange": { "total": 0.057087427999931606, "count": 1, "is_parallel": true, "self": 0.057087427999931606 }, "steps_from_proto": { "total": 0.001965659000006781, "count": 1, "is_parallel": true, "self": 0.0004133859997637046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015522730002430762, "count": 8, "is_parallel": true, "self": 0.0015522730002430762 } } } } } } }, "UnityEnvironment.step": { "total": 1531.3579650500192, "count": 63533, "is_parallel": true, "self": 42.22339781407186, "children": { "UnityEnvironment._generate_step_input": { "total": 28.96040884197282, "count": 63533, "is_parallel": true, "self": 28.96040884197282 }, "communicator.exchange": { "total": 1338.3770215899954, "count": 63533, "is_parallel": true, "self": 1338.3770215899954 }, "steps_from_proto": { "total": 121.79713680397913, "count": 63533, "is_parallel": true, "self": 26.09678466014475, "children": { "_process_rank_one_or_two_observation": { "total": 95.70035214383438, "count": 508264, "is_parallel": true, "self": 95.70035214383438 } } } } } } } } } } }, "trainer_advance": { "total": 1050.6993991709603, "count": 63534, "self": 4.37520735494968, "children": { "process_trajectory": { "total": 161.18849986601526, "count": 63534, "self": 160.85039563801593, "children": { "RLTrainer._checkpoint": { "total": 0.33810422799933804, "count": 2, "self": 0.33810422799933804 } } }, "_update_policy": { "total": 885.1356919499954, "count": 452, "self": 354.39822970496834, "children": { "TorchPPOOptimizer.update": { "total": 530.737462245027, "count": 22773, "self": 530.737462245027 } } } } } } }, "trainer_threads": { "total": 1.5489995348616503e-06, "count": 1, "self": 1.5489995348616503e-06 }, "TrainerController._save_models": { "total": 0.11860725600035948, "count": 1, "self": 0.004090922000614228, "children": { "RLTrainer._checkpoint": { "total": 0.11451633399974526, "count": 1, "self": 0.11451633399974526 } } } } } } }