{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4364793002605438, "min": 0.43097931146621704, "max": 1.348204493522644, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12982.640625, "min": 12956.9619140625, "max": 40899.1328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5792258977890015, "min": -0.1020701453089714, "max": 0.5792258977890015, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.28712463378906, "min": -24.70097541809082, "max": 159.28712463378906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06211266294121742, "min": -0.0010821776231750846, "max": 0.43646571040153503, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.080982208251953, "min": -0.29976320266723633, "max": 103.44237518310547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06422355902290697, "min": 0.06422355902290697, "max": 0.07274318585306355, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9633533853436045, "min": 0.5062263699669267, "max": 1.063254190774922, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013843928579449518, "min": 0.0009165371813543917, "max": 0.014682381626958629, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20765892869174277, "min": 0.011914983357607092, "max": 0.20765892869174277, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.516837494420003e-06, "min": 7.516837494420003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011275256241630004, "min": 0.00011275256241630004, "max": 0.0035076584307805994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250558, "min": 0.10250558, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375836999999999, "min": 1.3886848, "max": 2.5692194000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603074420000001, "min": 0.0002603074420000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039046116300000015, "min": 0.0039046116300000015, "max": 0.11694501806, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011865820735692978, "min": 0.011865820735692978, "max": 0.6456736326217651, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17798730731010437, "min": 0.16781944036483765, "max": 4.519715309143066, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.75581395348837, "min": 355.75581395348837, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30595.0, "min": 15984.0, "max": 32966.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6209790521236354, "min": -1.0000000521540642, "max": 1.6209790521236354, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.40419848263264, "min": -29.91600164026022, "max": 139.40419848263264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6209790521236354, "min": -1.0000000521540642, "max": 1.6209790521236354, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.40419848263264, "min": -29.91600164026022, "max": 139.40419848263264, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04361349662602067, "min": 0.04361349662602067, "max": 12.353539424017072, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7507607098377775, "min": 3.5530925758212106, "max": 197.65663078427315, "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": "1686225171", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1686227424" }, "total": 2253.109547481, "count": 1, "self": 1.3950652530002117, "children": { "run_training.setup": { "total": 0.03797552400010318, "count": 1, "self": 0.03797552400010318 }, "TrainerController.start_learning": { "total": 2251.6765067039996, "count": 1, "self": 1.3656839180071074, "children": { "TrainerController._reset_env": { "total": 4.910869410000032, "count": 1, "self": 4.910869410000032 }, "TrainerController.advance": { "total": 2245.2508095739927, "count": 63639, "self": 1.3939744659901407, "children": { "env_step": { "total": 1599.2007582459473, "count": 63639, "self": 1485.8110724349392, "children": { "SubprocessEnvManager._take_step": { "total": 112.56985956005997, "count": 63639, "self": 4.93372276602031, "children": { "TorchPolicy.evaluate": { "total": 107.63613679403966, "count": 62556, "self": 107.63613679403966 } } }, "workers": { "total": 0.8198262509481538, "count": 63639, "self": 0.0, "children": { "worker_root": { "total": 2246.2700504209784, "count": 63639, "is_parallel": true, "self": 876.9957763769708, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018993099999988772, "count": 1, "is_parallel": true, "self": 0.0006564210000306048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012428889999682724, "count": 8, "is_parallel": true, "self": 0.0012428889999682724 } } }, "UnityEnvironment.step": { "total": 0.0857466900001782, "count": 1, "is_parallel": true, "self": 0.0006125650002104521, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005276749998301966, "count": 1, "is_parallel": true, "self": 0.0005276749998301966 }, "communicator.exchange": { "total": 0.08047958900010599, "count": 1, "is_parallel": true, "self": 0.08047958900010599 }, "steps_from_proto": { "total": 0.0041268610000315675, "count": 1, "is_parallel": true, "self": 0.00042779999989761563, "children": { "_process_rank_one_or_two_observation": { "total": 0.003699061000133952, "count": 8, "is_parallel": true, "self": 0.003699061000133952 } } } } } } }, "UnityEnvironment.step": { "total": 1369.2742740440076, "count": 63638, "is_parallel": true, "self": 31.827990199037004, "children": { "UnityEnvironment._generate_step_input": { "total": 24.715550884967797, "count": 63638, "is_parallel": true, "self": 24.715550884967797 }, "communicator.exchange": { "total": 1207.5641165870065, "count": 63638, "is_parallel": true, "self": 1207.5641165870065 }, "steps_from_proto": { "total": 105.16661637299626, "count": 63638, "is_parallel": true, "self": 21.719195842886393, "children": { "_process_rank_one_or_two_observation": { "total": 83.44742053010987, "count": 509104, "is_parallel": true, "self": 83.44742053010987 } } } } } } } } } } }, "trainer_advance": { "total": 644.6560768620552, "count": 63639, "self": 2.680193536055185, "children": { "process_trajectory": { "total": 112.94083518599973, "count": 63639, "self": 112.56928921300005, "children": { "RLTrainer._checkpoint": { "total": 0.3715459729996837, "count": 2, "self": 0.3715459729996837 } } }, "_update_policy": { "total": 529.0350481400003, "count": 448, "self": 341.5171298019625, "children": { "TorchPPOOptimizer.update": { "total": 187.51791833803782, "count": 22776, "self": 187.51791833803782 } } } } } } }, "trainer_threads": { "total": 1.3599997146229725e-06, "count": 1, "self": 1.3599997146229725e-06 }, "TrainerController._save_models": { "total": 0.14914244200008397, "count": 1, "self": 0.0017961730000024545, "children": { "RLTrainer._checkpoint": { "total": 0.14734626900008152, "count": 1, "self": 0.14734626900008152 } } } } } } }