{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3097107410430908, "min": 0.3097107410430908, "max": 1.4449098110198975, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9340.8759765625, "min": 9340.8759765625, "max": 43832.78515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5843120217323303, "min": -0.09782957285642624, "max": 0.5843120217323303, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.19168090820312, "min": -23.576927185058594, "max": 164.19168090820312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01212588232010603, "min": -0.01472766324877739, "max": 0.2872449457645416, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.4073729515075684, "min": -4.094290256500244, "max": 68.64412689208984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06886959983135707, "min": 0.0651354297866217, "max": 0.07464760874351747, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.964174397638999, "min": 0.514063240745976, "max": 1.0463412161528443, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015278510514084093, "min": 0.0008820909118892131, "max": 0.015278510514084093, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21389914719717731, "min": 0.012349272766448984, "max": 0.21389914719717731, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.657833161707143e-06, "min": 7.657833161707143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010720966426390001, "min": 0.00010720966426390001, "max": 0.0036329995890002006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255257857142855, "min": 0.10255257857142855, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357360999999997, "min": 1.3886848, "max": 2.6109998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002650025992857144, "min": 0.0002650025992857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037100363900000014, "min": 0.0037100363900000014, "max": 0.12111888002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01142672449350357, "min": 0.01142672449350357, "max": 0.5521621108055115, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15997414290905, "min": 0.15997414290905, "max": 3.8651349544525146, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 320.9789473684211, "min": 315.468085106383, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30493.0, "min": 15984.0, "max": 32718.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6649489164986508, "min": -1.0000000521540642, "max": 1.6649489164986508, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.50519815087318, "min": -30.450401715934277, "max": 156.50519815087318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6649489164986508, "min": -1.0000000521540642, "max": 1.6649489164986508, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.50519815087318, "min": -30.450401715934277, "max": 156.50519815087318, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03733891869450553, "min": 0.03733891869450553, "max": 11.715524667873979, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5098583572835196, "min": 3.5098583572835196, "max": 187.44839468598366, "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": "1704161004", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704163163" }, "total": 2159.20083303, "count": 1, "self": 0.4899595650003903, "children": { "run_training.setup": { "total": 0.047760527999798796, "count": 1, "self": 0.047760527999798796 }, "TrainerController.start_learning": { "total": 2158.663112937, "count": 1, "self": 1.2137615479387023, "children": { "TrainerController._reset_env": { "total": 2.0577819490004003, "count": 1, "self": 2.0577819490004003 }, "TrainerController.advance": { "total": 2155.30776770706, "count": 63918, "self": 1.3057424270750744, "children": { "env_step": { "total": 1540.6294989880525, "count": 63918, "self": 1418.444812664045, "children": { "SubprocessEnvManager._take_step": { "total": 121.4126936570351, "count": 63918, "self": 4.483221149911969, "children": { "TorchPolicy.evaluate": { "total": 116.92947250712314, "count": 62553, "self": 116.92947250712314 } } }, "workers": { "total": 0.7719926669724373, "count": 63918, "self": 0.0, "children": { "worker_root": { "total": 2153.7768679780365, "count": 63918, "is_parallel": true, "self": 846.6006978761425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017456580003454292, "count": 1, "is_parallel": true, "self": 0.00049270899990006, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012529490004453692, "count": 8, "is_parallel": true, "self": 0.0012529490004453692 } } }, "UnityEnvironment.step": { "total": 0.04957278800020504, "count": 1, "is_parallel": true, "self": 0.0005692079998880217, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047341900017272565, "count": 1, "is_parallel": true, "self": 0.00047341900017272565 }, "communicator.exchange": { "total": 0.04693320500018672, "count": 1, "is_parallel": true, "self": 0.04693320500018672 }, "steps_from_proto": { "total": 0.0015969559999575722, "count": 1, "is_parallel": true, "self": 0.00032938900039880536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012675669995587668, "count": 8, "is_parallel": true, "self": 0.0012675669995587668 } } } } } } }, "UnityEnvironment.step": { "total": 1307.176170101894, "count": 63917, "is_parallel": true, "self": 34.000770916954025, "children": { "UnityEnvironment._generate_step_input": { "total": 23.138895098916237, "count": 63917, "is_parallel": true, "self": 23.138895098916237 }, "communicator.exchange": { "total": 1154.4888969790436, "count": 63917, "is_parallel": true, "self": 1154.4888969790436 }, "steps_from_proto": { "total": 95.5476071069802, "count": 63917, "is_parallel": true, "self": 18.578547215598974, "children": { "_process_rank_one_or_two_observation": { "total": 76.96905989138122, "count": 511336, "is_parallel": true, "self": 76.96905989138122 } } } } } } } } } } }, "trainer_advance": { "total": 613.3725262919324, "count": 63918, "self": 2.4800740438317916, "children": { "process_trajectory": { "total": 123.52159773710218, "count": 63918, "self": 123.34020753010327, "children": { "RLTrainer._checkpoint": { "total": 0.18139020699891262, "count": 2, "self": 0.18139020699891262 } } }, "_update_policy": { "total": 487.37085451099847, "count": 455, "self": 286.5776960729545, "children": { "TorchPPOOptimizer.update": { "total": 200.79315843804397, "count": 22794, "self": 200.79315843804397 } } } } } } }, "trainer_threads": { "total": 1.2420005077729002e-06, "count": 1, "self": 1.2420005077729002e-06 }, "TrainerController._save_models": { "total": 0.0838004910001473, "count": 1, "self": 0.0014953540003261878, "children": { "RLTrainer._checkpoint": { "total": 0.08230513699982112, "count": 1, "self": 0.08230513699982112 } } } } } } }