{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5210186839103699, "min": 0.5210186839103699, "max": 1.394187092781067, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15388.8076171875, "min": 15388.8076171875, "max": 42294.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38211846351623535, "min": -0.12940175831317902, "max": 0.40134376287460327, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.8792724609375, "min": -31.18582534790039, "max": 104.75072479248047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05048336461186409, "min": -0.012663637287914753, "max": 0.44180378317832947, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.327608108520508, "min": -3.2545547485351562, "max": 104.7074966430664, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06502506179857022, "min": 0.06502506179857022, "max": 0.07288621204677627, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9103508651799831, "min": 0.499187882807997, "max": 1.0803796666344472, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012707159167759873, "min": 0.0002521159301883774, "max": 0.012959194310274647, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17790022834863822, "min": 0.0032775070924489064, "max": 0.1943879146541197, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.442690376278572e-06, "min": 7.442690376278572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001041976652679, "min": 0.0001041976652679, "max": 0.0037577476474174986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024808642857143, "min": 0.1024808642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347321000000002, "min": 1.3886848, "max": 2.6525825, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002578383421428572, "min": 0.0002578383421428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003609736790000001, "min": 0.003609736790000001, "max": 0.12527299174999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008895041421055794, "min": 0.008875316940248013, "max": 0.537865400314331, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12453058362007141, "min": 0.12425443530082703, "max": 3.7650578022003174, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.6190476190476, "min": 452.6190476190476, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28515.0, "min": 15984.0, "max": 33193.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.388596799520273, "min": -1.0000000521540642, "max": 1.388596799520273, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.4815983697772, "min": -30.99620160460472, "max": 87.4815983697772, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.388596799520273, "min": -1.0000000521540642, "max": 1.388596799520273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.4815983697772, "min": -30.99620160460472, "max": 87.4815983697772, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04187900251995343, "min": 0.04187900251995343, "max": 11.00344898737967, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6383771587570664, "min": 2.6383771587570664, "max": 176.05518379807472, "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": "1674009645", "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": "1674011611" }, "total": 1965.4390328949999, "count": 1, "self": 0.4247052119999353, "children": { "run_training.setup": { "total": 0.10637414999973771, "count": 1, "self": 0.10637414999973771 }, "TrainerController.start_learning": { "total": 1964.9079535330002, "count": 1, "self": 1.1892624331185289, "children": { "TrainerController._reset_env": { "total": 5.87035678500024, "count": 1, "self": 5.87035678500024 }, "TrainerController.advance": { "total": 1957.7664276318824, "count": 63501, "self": 1.2446527719580445, "children": { "env_step": { "total": 1317.4856910459612, "count": 63501, "self": 1214.5966142420157, "children": { "SubprocessEnvManager._take_step": { "total": 102.12345483303307, "count": 63501, "self": 4.265492831023948, "children": { "TorchPolicy.evaluate": { "total": 97.85796200200912, "count": 62570, "self": 32.93760185492465, "children": { "TorchPolicy.sample_actions": { "total": 64.92036014708447, "count": 62570, "self": 64.92036014708447 } } } } }, "workers": { "total": 0.7656219709124343, "count": 63501, "self": 0.0, "children": { "worker_root": { "total": 1960.5084490250092, "count": 63501, "is_parallel": true, "self": 843.8870077099537, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020266669998818543, "count": 1, "is_parallel": true, "self": 0.0008490120003443735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011776549995374808, "count": 8, "is_parallel": true, "self": 0.0011776549995374808 } } }, "UnityEnvironment.step": { "total": 0.04539603900002476, "count": 1, "is_parallel": true, "self": 0.000513739000325586, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004480789998524415, "count": 1, "is_parallel": true, "self": 0.0004480789998524415 }, "communicator.exchange": { "total": 0.042789405999883456, "count": 1, "is_parallel": true, "self": 0.042789405999883456 }, "steps_from_proto": { "total": 0.0016448149999632733, "count": 1, "is_parallel": true, "self": 0.00040842099997462356, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012363939999886497, "count": 8, "is_parallel": true, "self": 0.0012363939999886497 } } } } } } }, "UnityEnvironment.step": { "total": 1116.6214413150556, "count": 63500, "is_parallel": true, "self": 27.084042284887346, "children": { "UnityEnvironment._generate_step_input": { "total": 22.546412985985626, "count": 63500, "is_parallel": true, "self": 22.546412985985626 }, "communicator.exchange": { "total": 968.5026466701238, "count": 63500, "is_parallel": true, "self": 968.5026466701238 }, "steps_from_proto": { "total": 98.4883393740588, "count": 63500, "is_parallel": true, "self": 22.149019507201047, "children": { "_process_rank_one_or_two_observation": { "total": 76.33931986685775, "count": 508000, "is_parallel": true, "self": 76.33931986685775 } } } } } } } } } } }, "trainer_advance": { "total": 639.0360838139632, "count": 63501, "self": 2.3602896728862106, "children": { "process_trajectory": { "total": 145.5156647390686, "count": 63501, "self": 145.33581110406885, "children": { "RLTrainer._checkpoint": { "total": 0.17985363499974483, "count": 2, "self": 0.17985363499974483 } } }, "_update_policy": { "total": 491.16012940200835, "count": 455, "self": 187.35240937702292, "children": { "TorchPPOOptimizer.update": { "total": 303.80772002498543, "count": 22794, "self": 303.80772002498543 } } } } } } }, "trainer_threads": { "total": 7.679991540499032e-07, "count": 1, "self": 7.679991540499032e-07 }, "TrainerController._save_models": { "total": 0.08190591499987931, "count": 1, "self": 0.0013051269997959025, "children": { "RLTrainer._checkpoint": { "total": 0.08060078800008341, "count": 1, "self": 0.08060078800008341 } } } } } } }