{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8309333920478821, "min": 0.7656899690628052, "max": 1.4269022941589355, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 24741.873046875, "min": 23031.955078125, "max": 43286.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989885.0, "min": 29992.0, "max": 989885.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989885.0, "min": 29992.0, "max": 989885.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1405208855867386, "min": -0.12913912534713745, "max": 0.19079013168811798, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 34.98970031738281, "min": -31.122528076171875, "max": 48.26990509033203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.20474326610565186, "min": 0.004859844222664833, "max": 0.6912320256233215, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 50.98107147216797, "min": 1.205241322517395, "max": 174.88169860839844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06836742489637497, "min": 0.06377940425325783, "max": 0.07218071716644694, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9571439485492497, "min": 0.5723626418202422, "max": 1.0487616927615213, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015659998553192483, "min": 9.052960041567619e-05, "max": 0.0793208630263306, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21923997974469478, "min": 0.0012674144058194667, "max": 1.1104920823686284, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.263547578849997e-06, "min": 7.263547578849997e-06, "max": 0.0002950068016644, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010168966610389997, "min": 0.00010168966610389997, "max": 0.0034902637365788, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242115000000003, "min": 0.10242115000000003, "max": 0.1983356, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338961000000003, "min": 1.4338961000000003, "max": 2.4634212000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002518728849999999, "min": 0.0002518728849999999, "max": 0.00983372644, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003526220389999999, "min": 0.003526220389999999, "max": 0.11635577788, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013673873618245125, "min": 0.013673873618245125, "max": 0.43400415778160095, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19143423438072205, "min": 0.19143423438072205, "max": 3.4720332622528076, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 690.1627906976744, "min": 656.9111111111112, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29677.0, "min": 16151.0, "max": 32872.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6584743779412535, "min": -0.9999419888181071, "max": 0.8718408766117963, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 28.314398251473904, "min": -31.99680170416832, "max": 38.43059856444597, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6584743779412535, "min": -0.9999419888181071, "max": 0.8718408766117963, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 28.314398251473904, "min": -31.99680170416832, "max": 38.43059856444597, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09807656830052174, "min": 0.094762589812227, "max": 8.442287031342001, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.217292436922435, "min": 4.085476721636951, "max": 143.51887953281403, "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": "1681747735", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=Pyramids Training --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": "1681749694" }, "total": 1959.1858688480002, "count": 1, "self": 0.4247120840000207, "children": { "run_training.setup": { "total": 0.1948925080000663, "count": 1, "self": 0.1948925080000663 }, "TrainerController.start_learning": { "total": 1958.566264256, "count": 1, "self": 1.27253303999305, "children": { "TrainerController._reset_env": { "total": 3.974899708999601, "count": 1, "self": 3.974899708999601 }, "TrainerController.advance": { "total": 1953.230559373007, "count": 63242, "self": 1.2752637819471602, "children": { "env_step": { "total": 1354.4223365219223, "count": 63242, "self": 1252.6824389328472, "children": { "SubprocessEnvManager._take_step": { "total": 100.98307905204638, "count": 63242, "self": 4.430808442119542, "children": { "TorchPolicy.evaluate": { "total": 96.55227060992684, "count": 62552, "self": 96.55227060992684 } } }, "workers": { "total": 0.756818537028721, "count": 63242, "self": 0.0, "children": { "worker_root": { "total": 1954.1881676339158, "count": 63242, "is_parallel": true, "self": 805.0407265630829, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018329019999328011, "count": 1, "is_parallel": true, "self": 0.0005069139997431193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013259880001896818, "count": 8, "is_parallel": true, "self": 0.0013259880001896818 } } }, "UnityEnvironment.step": { "total": 0.06754762199989273, "count": 1, "is_parallel": true, "self": 0.0005847819998052728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005002319999221072, "count": 1, "is_parallel": true, "self": 0.0005002319999221072 }, "communicator.exchange": { "total": 0.06300158099975306, "count": 1, "is_parallel": true, "self": 0.06300158099975306 }, "steps_from_proto": { "total": 0.0034610270004122867, "count": 1, "is_parallel": true, "self": 0.0021101189995533787, "children": { "_process_rank_one_or_two_observation": { "total": 0.001350908000858908, "count": 8, "is_parallel": true, "self": 0.001350908000858908 } } } } } } }, "UnityEnvironment.step": { "total": 1149.1474410708329, "count": 63241, "is_parallel": true, "self": 31.40883217578721, "children": { "UnityEnvironment._generate_step_input": { "total": 22.62093249196687, "count": 63241, "is_parallel": true, "self": 22.62093249196687 }, "communicator.exchange": { "total": 1005.025426198094, "count": 63241, "is_parallel": true, "self": 1005.025426198094 }, "steps_from_proto": { "total": 90.0922502049848, "count": 63241, "is_parallel": true, "self": 18.901785092849423, "children": { "_process_rank_one_or_two_observation": { "total": 71.19046511213537, "count": 505928, "is_parallel": true, "self": 71.19046511213537 } } } } } } } } } } }, "trainer_advance": { "total": 597.5329590691376, "count": 63242, "self": 2.31939269210352, "children": { "process_trajectory": { "total": 100.20375061803088, "count": 63242, "self": 100.00279281103167, "children": { "RLTrainer._checkpoint": { "total": 0.20095780699921306, "count": 2, "self": 0.20095780699921306 } } }, "_update_policy": { "total": 495.00981575900323, "count": 448, "self": 314.4164968800069, "children": { "TorchPPOOptimizer.update": { "total": 180.59331887899634, "count": 22794, "self": 180.59331887899634 } } } } } } }, "trainer_threads": { "total": 9.73000169324223e-07, "count": 1, "self": 9.73000169324223e-07 }, "TrainerController._save_models": { "total": 0.08827116100019339, "count": 1, "self": 0.0014144480001050397, "children": { "RLTrainer._checkpoint": { "total": 0.08685671300008835, "count": 1, "self": 0.08685671300008835 } } } } } } }