{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41706031560897827, "min": 0.39987367391586304, "max": 1.4265919923782349, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12478.4443359375, "min": 11893.8427734375, "max": 43277.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5445380806922913, "min": -0.10263730585575104, "max": 0.6031022667884827, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.6588897705078, "min": -24.64433479309082, "max": 171.2810516357422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031249234452843666, "min": -0.022456614300608635, "max": 0.3082523047924042, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.531041145324707, "min": -6.130655765533447, "max": 74.28880310058594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06906192031306155, "min": 0.06509264032744493, "max": 0.07407177619473382, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9668668843828617, "min": 0.5185024333631367, "max": 1.0636535098504585, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01644032014430669, "min": 0.0001914167155569591, "max": 0.01644032014430669, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23016448202029363, "min": 0.002297000586683509, "max": 0.23016448202029363, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3445046947214265e-06, "min": 7.3445046947214265e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010282306572609997, "min": 0.00010282306572609997, "max": 0.0030212147929284997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244813571428572, "min": 0.10244813571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342739000000002, "min": 1.3886848, "max": 2.3173182999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025456875785714287, "min": 0.00025456875785714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00356396261, "min": 0.00356396261, "max": 0.10073644285, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01132919080555439, "min": 0.01096200942993164, "max": 0.4227558970451355, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15860867500305176, "min": 0.1564677506685257, "max": 2.9592912197113037, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.4642857142857, "min": 317.4736842105263, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29775.0, "min": 15984.0, "max": 32627.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5740904557917799, "min": -1.0000000521540642, "max": 1.67442103012612, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.2235982865095, "min": -30.999801620841026, "max": 159.0699978619814, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5740904557917799, "min": -1.0000000521540642, "max": 1.67442103012612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.2235982865095, "min": -30.999801620841026, "max": 159.0699978619814, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041742808970628265, "min": 0.040282592770688415, "max": 8.288749422878027, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.506395953532774, "min": 3.3434551999671385, "max": 132.61999076604843, "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": "1674037595", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674039569" }, "total": 1974.5286894119995, "count": 1, "self": 0.4250200039991796, "children": { "run_training.setup": { "total": 0.09632757899998978, "count": 1, "self": 0.09632757899998978 }, "TrainerController.start_learning": { "total": 1974.0073418290003, "count": 1, "self": 1.108627788949434, "children": { "TrainerController._reset_env": { "total": 5.894044652000048, "count": 1, "self": 5.894044652000048 }, "TrainerController.advance": { "total": 1966.9217337020505, "count": 63715, "self": 1.2011862048698276, "children": { "env_step": { "total": 1326.904724606174, "count": 63715, "self": 1225.3835623730788, "children": { "SubprocessEnvManager._take_step": { "total": 100.79467567509528, "count": 63715, "self": 4.300358689026325, "children": { "TorchPolicy.evaluate": { "total": 96.49431698606895, "count": 62558, "self": 32.60728600597122, "children": { "TorchPolicy.sample_actions": { "total": 63.887030980097734, "count": 62558, "self": 63.887030980097734 } } } } }, "workers": { "total": 0.7264865580000333, "count": 63715, "self": 0.0, "children": { "worker_root": { "total": 1969.9138176189772, "count": 63715, "is_parallel": true, "self": 839.1564808049266, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016923130001487152, "count": 1, "is_parallel": true, "self": 0.0006279349995566008, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010643780005921144, "count": 8, "is_parallel": true, "self": 0.0010643780005921144 } } }, "UnityEnvironment.step": { "total": 0.047100884999963455, "count": 1, "is_parallel": true, "self": 0.0004843809997510107, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004671970000345027, "count": 1, "is_parallel": true, "self": 0.0004671970000345027 }, "communicator.exchange": { "total": 0.04459072899999228, "count": 1, "is_parallel": true, "self": 0.04459072899999228 }, "steps_from_proto": { "total": 0.001558578000185662, "count": 1, "is_parallel": true, "self": 0.00040575100047135493, "children": { "_process_rank_one_or_two_observation": { "total": 0.001152826999714307, "count": 8, "is_parallel": true, "self": 0.001152826999714307 } } } } } } }, "UnityEnvironment.step": { "total": 1130.7573368140506, "count": 63714, "is_parallel": true, "self": 26.583615341010955, "children": { "UnityEnvironment._generate_step_input": { "total": 22.578934566002317, "count": 63714, "is_parallel": true, "self": 22.578934566002317 }, "communicator.exchange": { "total": 982.7525736099897, "count": 63714, "is_parallel": true, "self": 982.7525736099897 }, "steps_from_proto": { "total": 98.84221329704769, "count": 63714, "is_parallel": true, "self": 21.707879949323797, "children": { "_process_rank_one_or_two_observation": { "total": 77.1343333477239, "count": 509712, "is_parallel": true, "self": 77.1343333477239 } } } } } } } } } } }, "trainer_advance": { "total": 638.8158228910065, "count": 63715, "self": 1.9402244029511166, "children": { "process_trajectory": { "total": 145.13831862504867, "count": 63715, "self": 144.9572564970481, "children": { "RLTrainer._checkpoint": { "total": 0.1810621280005762, "count": 2, "self": 0.1810621280005762 } } }, "_update_policy": { "total": 491.73727986300673, "count": 437, "self": 186.49400502595563, "children": { "TorchPPOOptimizer.update": { "total": 305.2432748370511, "count": 22884, "self": 305.2432748370511 } } } } } } }, "trainer_threads": { "total": 1.190000148199033e-06, "count": 1, "self": 1.190000148199033e-06 }, "TrainerController._save_models": { "total": 0.0829344960002345, "count": 1, "self": 0.001292480000302021, "children": { "RLTrainer._checkpoint": { "total": 0.08164201599993248, "count": 1, "self": 0.08164201599993248 } } } } } } }