{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38775911927223206, "min": 0.38775911927223206, "max": 1.4447251558303833, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11657.58984375, "min": 11657.58984375, "max": 43827.18359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05246651545166969, "min": -0.0905514657497406, "max": 0.23829002678394318, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 12.906763076782227, "min": -21.732351303100586, "max": 60.525665283203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.5624829530715942, "min": -0.5624829530715942, "max": 0.6832317113876343, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -138.3708038330078, "min": -140.74761962890625, "max": 175.59054565429688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06546499676554376, "min": 0.06546499676554376, "max": 0.07267681104831653, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9165099547176128, "min": 0.4796702407824675, "max": 1.0274916140536103, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.15456800450219024, "min": 0.0009616968275398592, "max": 0.15456800450219024, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.1639520630306635, "min": 0.01154036193047831, "max": 2.1639520630306635, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.7901974033e-06, "min": 7.7901974033e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001090627636462, "min": 0.0001090627636462, "max": 0.0033823475725508994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025967, "min": 0.1025967, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4363538, "min": 1.3886848, "max": 2.572478700000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026941033, "min": 0.00026941033, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037717446200000006, "min": 0.0037717446200000006, "max": 0.11277216508999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016598481684923172, "min": 0.016598481684923172, "max": 0.5532055497169495, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.232378751039505, "min": 0.232378751039505, "max": 3.872438907623291, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 813.1111111111111, "min": 580.5961538461538, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29272.0, "min": 15984.0, "max": 33423.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.07543329708278179, "min": -1.0000000521540642, "max": 0.9577384284482553, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 2.7155986949801445, "min": -29.93500157445669, "max": 49.80239827930927, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.07543329708278179, "min": -1.0000000521540642, "max": 0.9577384284482553, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 2.7155986949801445, "min": -29.93500157445669, "max": 49.80239827930927, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1388718311053607, "min": 0.11388524502063564, "max": 11.111493222415447, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.999385919792985, "min": 4.950408442469779, "max": 177.78389155864716, "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": "1689707469", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/arran/.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": "1689708328" }, "total": 859.6129147850006, "count": 1, "self": 0.21771338100370485, "children": { "run_training.setup": { "total": 0.008955823999713175, "count": 1, "self": 0.008955823999713175 }, "TrainerController.start_learning": { "total": 859.3862455799972, "count": 1, "self": 0.6880475761281559, "children": { "TrainerController._reset_env": { "total": 2.2255473999975948, "count": 1, "self": 2.2255473999975948 }, "TrainerController.advance": { "total": 856.4098104708828, "count": 63352, "self": 0.644764416050748, "children": { "env_step": { "total": 495.48123582721746, "count": 63352, "self": 412.2881297392305, "children": { "SubprocessEnvManager._take_step": { "total": 82.77501309885702, "count": 63352, "self": 2.1328031722077867, "children": { "TorchPolicy.evaluate": { "total": 80.64220992664923, "count": 62569, "self": 80.64220992664923 } } }, "workers": { "total": 0.41809298912994564, "count": 63352, "self": 0.0, "children": { "worker_root": { "total": 858.3867076142051, "count": 63352, "is_parallel": true, "self": 492.16968337741855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010899920016527176, "count": 1, "is_parallel": true, "self": 0.0002725080121308565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008174839895218611, "count": 8, "is_parallel": true, "self": 0.0008174839895218611 } } }, "UnityEnvironment.step": { "total": 0.02295126400713343, "count": 1, "is_parallel": true, "self": 0.00021440500859171152, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020064000273123384, "count": 1, "is_parallel": true, "self": 0.00020064000273123384 }, "communicator.exchange": { "total": 0.021891077994951047, "count": 1, "is_parallel": true, "self": 0.021891077994951047 }, "steps_from_proto": { "total": 0.0006451410008594394, "count": 1, "is_parallel": true, "self": 0.00015810898912604898, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004870320117333904, "count": 8, "is_parallel": true, "self": 0.0004870320117333904 } } } } } } }, "UnityEnvironment.step": { "total": 366.21702423678653, "count": 63351, "is_parallel": true, "self": 12.40942198477569, "children": { "UnityEnvironment._generate_step_input": { "total": 9.221894537040498, "count": 63351, "is_parallel": true, "self": 9.221894537040498 }, "communicator.exchange": { "total": 308.2674282877997, "count": 63351, "is_parallel": true, "self": 308.2674282877997 }, "steps_from_proto": { "total": 36.31827942717064, "count": 63351, "is_parallel": true, "self": 7.995214811657206, "children": { "_process_rank_one_or_two_observation": { "total": 28.32306461551343, "count": 506808, "is_parallel": true, "self": 28.32306461551343 } } } } } } } } } } }, "trainer_advance": { "total": 360.2838102276146, "count": 63352, "self": 1.2734898106136825, "children": { "process_trajectory": { "total": 64.03899535318487, "count": 63352, "self": 63.902627798190224, "children": { "RLTrainer._checkpoint": { "total": 0.13636755499464925, "count": 2, "self": 0.13636755499464925 } } }, "_update_policy": { "total": 294.97132506381604, "count": 448, "self": 179.79453930055024, "children": { "TorchPPOOptimizer.update": { "total": 115.1767857632658, "count": 22773, "self": 115.1767857632658 } } } } } } }, "trainer_threads": { "total": 5.409965524449944e-07, "count": 1, "self": 5.409965524449944e-07 }, "TrainerController._save_models": { "total": 0.06283959199208766, "count": 1, "self": 0.0007559409859823063, "children": { "RLTrainer._checkpoint": { "total": 0.062083651006105356, "count": 1, "self": 0.062083651006105356 } } } } } } }