{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23297137022018433, "min": 0.21157538890838623, "max": 1.3655118942260742, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6977.95849609375, "min": 6357.41748046875, "max": 41424.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5262762904167175, "min": -0.19615019857883453, "max": 0.6083706617355347, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.72598266601562, "min": -46.48759841918945, "max": 170.9521484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0064531611278653145, "min": -0.0064531611278653145, "max": 0.4995083808898926, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.7746193408966064, "min": -1.7746193408966064, "max": 118.38348388671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0690342742072207, "min": 0.06555259116811656, "max": 0.07352872456734379, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9664798389010898, "min": 0.5030814734840867, "max": 1.1028029757435434, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016259669899721683, "min": 0.0014329635433919753, "max": 0.016259669899721683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22763537859610358, "min": 0.012896671890527778, "max": 0.23817671794677153, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.62740460042143e-06, "min": 7.62740460042143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010678366440590002, "min": 0.00010678366440590002, "max": 0.0036336994887668996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025424357142857, "min": 0.1025424357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355940999999999, "min": 1.3886848, "max": 2.6112331000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002639893278571429, "min": 0.0002639893278571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003695850590000001, "min": 0.003695850590000001, "max": 0.12114218669, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012653774581849575, "min": 0.011542811058461666, "max": 0.5906227827072144, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1771528422832489, "min": 0.16159935295581818, "max": 4.134359359741211, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.4597701149425, "min": 307.2842105263158, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28750.0, "min": 15984.0, "max": 34544.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.554565504792778, "min": -1.0000000521540642, "max": 1.608486297569777, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.24719891697168, "min": -29.152201764285564, "max": 152.8061982691288, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.554565504792778, "min": -1.0000000521540642, "max": 1.608486297569777, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.24719891697168, "min": -29.152201764285564, "max": 152.8061982691288, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04355037355348575, "min": 0.04308971196082176, "max": 11.917101632803679, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.78888249915326, "min": 3.6592654721753206, "max": 190.67362612485886, "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": "1698344773", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698347134" }, "total": 2360.9528336760004, "count": 1, "self": 0.4908952280011363, "children": { "run_training.setup": { "total": 0.07102503000010074, "count": 1, "self": 0.07102503000010074 }, "TrainerController.start_learning": { "total": 2360.3909134179994, "count": 1, "self": 1.5639647420252913, "children": { "TrainerController._reset_env": { "total": 3.820204004000061, "count": 1, "self": 3.820204004000061 }, "TrainerController.advance": { "total": 2354.9246315299733, "count": 63996, "self": 1.5690374621626688, "children": { "env_step": { "total": 1700.3897112769516, "count": 63996, "self": 1554.1335494589378, "children": { "SubprocessEnvManager._take_step": { "total": 145.29347375304133, "count": 63996, "self": 4.968374234062821, "children": { "TorchPolicy.evaluate": { "total": 140.3250995189785, "count": 62566, "self": 140.3250995189785 } } }, "workers": { "total": 0.9626880649725535, "count": 63996, "self": 0.0, "children": { "worker_root": { "total": 2354.9799347829016, "count": 63996, "is_parallel": true, "self": 926.0123415179355, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019381209999664861, "count": 1, "is_parallel": true, "self": 0.0006381220005096111, "children": { "_process_rank_one_or_two_observation": { "total": 0.001299998999456875, "count": 8, "is_parallel": true, "self": 0.001299998999456875 } } }, "UnityEnvironment.step": { "total": 0.08003846700012218, "count": 1, "is_parallel": true, "self": 0.0005977759999495902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004764889999933075, "count": 1, "is_parallel": true, "self": 0.0004764889999933075 }, "communicator.exchange": { "total": 0.07740171600016765, "count": 1, "is_parallel": true, "self": 0.07740171600016765 }, "steps_from_proto": { "total": 0.0015624860000116314, "count": 1, "is_parallel": true, "self": 0.00033565900025678275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012268269997548487, "count": 8, "is_parallel": true, "self": 0.0012268269997548487 } } } } } } }, "UnityEnvironment.step": { "total": 1428.9675932649661, "count": 63995, "is_parallel": true, "self": 36.36175975404262, "children": { "UnityEnvironment._generate_step_input": { "total": 24.954958330031786, "count": 63995, "is_parallel": true, "self": 24.954958330031786 }, "communicator.exchange": { "total": 1265.221783471943, "count": 63995, "is_parallel": true, "self": 1265.221783471943 }, "steps_from_proto": { "total": 102.42909170894882, "count": 63995, "is_parallel": true, "self": 21.197555764814297, "children": { "_process_rank_one_or_two_observation": { "total": 81.23153594413452, "count": 511960, "is_parallel": true, "self": 81.23153594413452 } } } } } } } } } } }, "trainer_advance": { "total": 652.9658827908588, "count": 63996, "self": 3.1025521708993438, "children": { "process_trajectory": { "total": 124.56737260595924, "count": 63996, "self": 124.40279876195905, "children": { "RLTrainer._checkpoint": { "total": 0.16457384400018782, "count": 2, "self": 0.16457384400018782 } } }, "_update_policy": { "total": 525.2959580140002, "count": 454, "self": 312.86833557398677, "children": { "TorchPPOOptimizer.update": { "total": 212.42762244001347, "count": 22752, "self": 212.42762244001347 } } } } } } }, "trainer_threads": { "total": 9.810000847210176e-07, "count": 1, "self": 9.810000847210176e-07 }, "TrainerController._save_models": { "total": 0.08211216100062302, "count": 1, "self": 0.0014332290002130321, "children": { "RLTrainer._checkpoint": { "total": 0.08067893200040999, "count": 1, "self": 0.08067893200040999 } } } } } } }