{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40617018938064575, "min": 0.369667112827301, "max": 1.4152188301086426, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12146.11328125, "min": 11190.912109375, "max": 42932.078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.561475932598114, "min": -0.09629026800394058, "max": 0.561475932598114, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.2132568359375, "min": -23.01337432861328, "max": 157.2132568359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0005570047651417553, "min": -0.002344713779166341, "max": 0.3042084574699402, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.15596133470535278, "min": -0.5885231494903564, "max": 73.0100326538086, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06857021602595018, "min": 0.06575287795192411, "max": 0.07368616528109886, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0285532403892526, "min": 0.5084936088054768, "max": 1.0751288530203358, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015416699145377303, "min": 0.00011032304136875945, "max": 0.01607185751033415, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23125048718065955, "min": 0.001213553455056354, "max": 0.23125048718065955, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.442117519326664e-06, "min": 7.442117519326664e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011163176278989996, "min": 0.00011163176278989996, "max": 0.003225551524816199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248067333333334, "min": 0.10248067333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372101, "min": 1.3691136000000002, "max": 2.3172423, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000257819266, "min": 0.000257819266, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038672889899999995, "min": 0.0038672889899999995, "max": 0.10753086162, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011612558737397194, "min": 0.011612558737397194, "max": 0.45031505823135376, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17418837547302246, "min": 0.1709676831960678, "max": 3.152205467224121, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.6741573033708, "min": 345.109756097561, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30765.0, "min": 15984.0, "max": 32998.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5419325672843482, "min": -1.0000000521540642, "max": 1.581702418897937, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.231998488307, "min": -32.000001668930054, "max": 137.231998488307, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5419325672843482, "min": -1.0000000521540642, "max": 1.581702418897937, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.231998488307, "min": -32.000001668930054, "max": 137.231998488307, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04128233964745939, "min": 0.04128233964745939, "max": 8.767852799966931, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6741282286238857, "min": 3.5938717161188833, "max": 140.2856447994709, "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": "1678649200", "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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678651566" }, "total": 2366.746772257, "count": 1, "self": 0.4869314289999238, "children": { "run_training.setup": { "total": 0.11426994499998955, "count": 1, "self": 0.11426994499998955 }, "TrainerController.start_learning": { "total": 2366.145570883, "count": 1, "self": 1.53678815404146, "children": { "TrainerController._reset_env": { "total": 9.353404302000001, "count": 1, "self": 9.353404302000001 }, "TrainerController.advance": { "total": 2355.158402126958, "count": 63607, "self": 1.6545828159732991, "children": { "env_step": { "total": 1659.7987794269716, "count": 63607, "self": 1539.6224163379698, "children": { "SubprocessEnvManager._take_step": { "total": 119.24217019103133, "count": 63607, "self": 5.223228071022504, "children": { "TorchPolicy.evaluate": { "total": 114.01894212000883, "count": 62558, "self": 114.01894212000883 } } }, "workers": { "total": 0.9341928979704903, "count": 63607, "self": 0.0, "children": { "worker_root": { "total": 2360.0372698160186, "count": 63607, "is_parallel": true, "self": 951.9878399540337, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004720517999999174, "count": 1, "is_parallel": true, "self": 0.003363345999957801, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013571720000413734, "count": 8, "is_parallel": true, "self": 0.0013571720000413734 } } }, "UnityEnvironment.step": { "total": 0.07745933600000399, "count": 1, "is_parallel": true, "self": 0.0005737449999969613, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004900289999909546, "count": 1, "is_parallel": true, "self": 0.0004900289999909546 }, "communicator.exchange": { "total": 0.07455900000002202, "count": 1, "is_parallel": true, "self": 0.07455900000002202 }, "steps_from_proto": { "total": 0.0018365619999940463, "count": 1, "is_parallel": true, "self": 0.0005418420000182778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012947199999757686, "count": 8, "is_parallel": true, "self": 0.0012947199999757686 } } } } } } }, "UnityEnvironment.step": { "total": 1408.049429861985, "count": 63606, "is_parallel": true, "self": 33.685560570938605, "children": { "UnityEnvironment._generate_step_input": { "total": 24.02109227200259, "count": 63606, "is_parallel": true, "self": 24.02109227200259 }, "communicator.exchange": { "total": 1251.5753313090484, "count": 63606, "is_parallel": true, "self": 1251.5753313090484 }, "steps_from_proto": { "total": 98.76744570999529, "count": 63606, "is_parallel": true, "self": 21.499778229007973, "children": { "_process_rank_one_or_two_observation": { "total": 77.26766748098731, "count": 508848, "is_parallel": true, "self": 77.26766748098731 } } } } } } } } } } }, "trainer_advance": { "total": 693.7050398840136, "count": 63607, "self": 2.6994267890302126, "children": { "process_trajectory": { "total": 130.30592685997834, "count": 63607, "self": 130.0844418909782, "children": { "RLTrainer._checkpoint": { "total": 0.22148496900013015, "count": 2, "self": 0.22148496900013015 } } }, "_update_policy": { "total": 560.699686235005, "count": 434, "self": 357.8411404290075, "children": { "TorchPPOOptimizer.update": { "total": 202.85854580599744, "count": 22836, "self": 202.85854580599744 } } } } } } }, "trainer_threads": { "total": 9.350001164420974e-07, "count": 1, "self": 9.350001164420974e-07 }, "TrainerController._save_models": { "total": 0.09697536500016213, "count": 1, "self": 0.001510387000053015, "children": { "RLTrainer._checkpoint": { "total": 0.09546497800010911, "count": 1, "self": 0.09546497800010911 } } } } } } }