{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35351136326789856, "min": 0.35351136326789856, "max": 1.462337613105774, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10741.0888671875, "min": 10529.3427734375, "max": 44361.47265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6317211389541626, "min": -0.09732968360185623, "max": 0.6317211389541626, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.04052734375, "min": -23.35912322998047, "max": 180.04052734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015244534239172935, "min": -0.011333020403981209, "max": 0.47815197706222534, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.344692230224609, "min": -3.09391450881958, "max": 113.322021484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07182447271424323, "min": 0.06384048991557706, "max": 0.07396131408228694, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0055426179994054, "min": 0.5177291985760086, "max": 1.0463872903880356, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01669079218395165, "min": 0.00023784085893341987, "max": 0.01669079218395165, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2336710905753231, "min": 0.0033297720250678783, "max": 0.2336710905753231, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4242832395571386e-06, "min": 7.4242832395571386e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010393996535379994, "min": 0.00010393996535379994, "max": 0.0035074358308547996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247472857142859, "min": 0.10247472857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346462000000002, "min": 1.3886848, "max": 2.5691452000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002572253842857142, "min": 0.0002572253842857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036011553799999985, "min": 0.0036011553799999985, "max": 0.11693760548, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011825679801404476, "min": 0.011825679801404476, "max": 0.34661319851875305, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16555951535701752, "min": 0.16555951535701752, "max": 2.4262924194335938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.81, "min": 301.81, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30181.0, "min": 15984.0, "max": 34228.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6570019938729026, "min": -1.0000000521540642, "max": 1.6570019938729026, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 164.04319739341736, "min": -31.998801663517952, "max": 164.04319739341736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6570019938729026, "min": -1.0000000521540642, "max": 1.6570019938729026, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 164.04319739341736, "min": -31.998801663517952, "max": 164.04319739341736, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03725801308448556, "min": 0.03725801308448556, "max": 7.061796880327165, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.68854329536407, "min": 3.68854329536407, "max": 112.98875008523464, "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": "1732800870", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732803289" }, "total": 2418.112402279, "count": 1, "self": 0.5273662149998017, "children": { "run_training.setup": { "total": 0.05507387999978164, "count": 1, "self": 0.05507387999978164 }, "TrainerController.start_learning": { "total": 2417.5299621840004, "count": 1, "self": 1.6224058069678904, "children": { "TrainerController._reset_env": { "total": 2.1480306069997823, "count": 1, "self": 2.1480306069997823 }, "TrainerController.advance": { "total": 2413.6750632430317, "count": 63983, "self": 1.5840653883442428, "children": { "env_step": { "total": 1696.6457993898198, "count": 63983, "self": 1531.716604830547, "children": { "SubprocessEnvManager._take_step": { "total": 163.98828243109892, "count": 63983, "self": 5.117535037122707, "children": { "TorchPolicy.evaluate": { "total": 158.87074739397622, "count": 62561, "self": 158.87074739397622 } } }, "workers": { "total": 0.9409121281737498, "count": 63983, "self": 0.0, "children": { "worker_root": { "total": 2411.8414503560684, "count": 63983, "is_parallel": true, "self": 1008.5991432350925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021426389998850937, "count": 1, "is_parallel": true, "self": 0.000672967999435059, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014696710004500346, "count": 8, "is_parallel": true, "self": 0.0014696710004500346 } } }, "UnityEnvironment.step": { "total": 0.047993433000101504, "count": 1, "is_parallel": true, "self": 0.0007641800002602395, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005025899999964167, "count": 1, "is_parallel": true, "self": 0.0005025899999964167 }, "communicator.exchange": { "total": 0.044990722999955324, "count": 1, "is_parallel": true, "self": 0.044990722999955324 }, "steps_from_proto": { "total": 0.0017359399998895242, "count": 1, "is_parallel": true, "self": 0.0003471049999461684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013888349999433558, "count": 8, "is_parallel": true, "self": 0.0013888349999433558 } } } } } } }, "UnityEnvironment.step": { "total": 1403.242307120976, "count": 63982, "is_parallel": true, "self": 35.07458299580594, "children": { "UnityEnvironment._generate_step_input": { "total": 24.469565787021565, "count": 63982, "is_parallel": true, "self": 24.469565787021565 }, "communicator.exchange": { "total": 1237.8802141060196, "count": 63982, "is_parallel": true, "self": 1237.8802141060196 }, "steps_from_proto": { "total": 105.81794423212887, "count": 63982, "is_parallel": true, "self": 22.34264649015222, "children": { "_process_rank_one_or_two_observation": { "total": 83.47529774197665, "count": 511856, "is_parallel": true, "self": 83.47529774197665 } } } } } } } } } } }, "trainer_advance": { "total": 715.4451984648676, "count": 63983, "self": 2.8982226149300914, "children": { "process_trajectory": { "total": 143.4256951969296, "count": 63983, "self": 143.2091575299296, "children": { "RLTrainer._checkpoint": { "total": 0.21653766700001142, "count": 2, "self": 0.21653766700001142 } } }, "_update_policy": { "total": 569.121280653008, "count": 448, "self": 321.3362275559921, "children": { "TorchPPOOptimizer.update": { "total": 247.78505309701586, "count": 22851, "self": 247.78505309701586 } } } } } } }, "trainer_threads": { "total": 9.740006134961732e-07, "count": 1, "self": 9.740006134961732e-07 }, "TrainerController._save_models": { "total": 0.08446155300043756, "count": 1, "self": 0.0014871650000713998, "children": { "RLTrainer._checkpoint": { "total": 0.08297438800036616, "count": 1, "self": 0.08297438800036616 } } } } } } }