{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6819160580635071, "min": 0.6629638075828552, "max": 1.51837158203125, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20173.8046875, "min": 19915.412109375, "max": 46061.3203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15569959580898285, "min": -0.11837504804134369, "max": 0.17404457926750183, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 39.236297607421875, "min": -28.52838706970215, "max": 43.68518829345703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007443465758115053, "min": 0.007443465758115053, "max": 0.2775042653083801, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.875753402709961, "min": 1.875753402709961, "max": 65.76850891113281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06699290539206744, "min": 0.06408625017045814, "max": 0.07272980823710957, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9379006754889441, "min": 0.4728908034181356, "max": 1.0771633558761098, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007444984943315574, "min": 6.690513093737361e-05, "max": 0.009175153382229422, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10422978920641804, "min": 0.0009366718331232306, "max": 0.13762730073344132, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.435383235857145e-06, "min": 7.435383235857145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010409536530200003, "min": 0.00010409536530200003, "max": 0.0030236870921044002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247842857142857, "min": 0.10247842857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434698, "min": 1.3691136000000002, "max": 2.3173566, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002575950142857143, "min": 0.0002575950142857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036063302000000005, "min": 0.0036063302000000005, "max": 0.10081877043999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012148250825703144, "min": 0.012148250825703144, "max": 0.34503912925720215, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17007550597190857, "min": 0.17007550597190857, "max": 2.415273904800415, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 703.6, "min": 693.4634146341464, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31662.0, "min": 15984.0, "max": 33053.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5406221856673559, "min": -1.0000000521540642, "max": 0.8140399737283588, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 24.327998355031013, "min": -32.000001668930054, "max": 32.56159894913435, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5406221856673559, "min": -1.0000000521540642, "max": 0.8140399737283588, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 24.327998355031013, "min": -32.000001668930054, "max": 32.56159894913435, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0879827772050501, "min": 0.0879827772050501, "max": 6.846857777796686, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9592249742272543, "min": 3.6500879912055098, "max": 109.54972444474697, "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": "1732036099", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1732038956" }, "total": 2856.238191001, "count": 1, "self": 0.7398672869994698, "children": { "run_training.setup": { "total": 0.11820819499985191, "count": 1, "self": 0.11820819499985191 }, "TrainerController.start_learning": { "total": 2855.3801155190004, "count": 1, "self": 2.2687031999748797, "children": { "TrainerController._reset_env": { "total": 6.362156989999903, "count": 1, "self": 6.362156989999903 }, "TrainerController.advance": { "total": 2846.593039698026, "count": 63182, "self": 2.381631643080709, "children": { "env_step": { "total": 1817.9159717169057, "count": 63182, "self": 1663.7332222608275, "children": { "SubprocessEnvManager._take_step": { "total": 152.84359284206357, "count": 63182, "self": 6.5422145490315415, "children": { "TorchPolicy.evaluate": { "total": 146.30137829303203, "count": 62556, "self": 146.30137829303203 } } }, "workers": { "total": 1.3391566140146551, "count": 63182, "self": 0.0, "children": { "worker_root": { "total": 2849.0949210699923, "count": 63182, "is_parallel": true, "self": 1352.0353206569912, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024923729999954958, "count": 1, "is_parallel": true, "self": 0.0007344349994582444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017579380005372514, "count": 8, "is_parallel": true, "self": 0.0017579380005372514 } } }, "UnityEnvironment.step": { "total": 0.06701166799985003, "count": 1, "is_parallel": true, "self": 0.0007330779997118952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004973550001068361, "count": 1, "is_parallel": true, "self": 0.0004973550001068361 }, "communicator.exchange": { "total": 0.0637939800001277, "count": 1, "is_parallel": true, "self": 0.0637939800001277 }, "steps_from_proto": { "total": 0.0019872549999035982, "count": 1, "is_parallel": true, "self": 0.0004332210000939085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015540339998096897, "count": 8, "is_parallel": true, "self": 0.0015540339998096897 } } } } } } }, "UnityEnvironment.step": { "total": 1497.0596004130011, "count": 63181, "is_parallel": true, "self": 47.85649653601081, "children": { "UnityEnvironment._generate_step_input": { "total": 29.995009046025416, "count": 63181, "is_parallel": true, "self": 29.995009046025416 }, "communicator.exchange": { "total": 1293.9749133059663, "count": 63181, "is_parallel": true, "self": 1293.9749133059663 }, "steps_from_proto": { "total": 125.2331815249986, "count": 63181, "is_parallel": true, "self": 26.472981750106328, "children": { "_process_rank_one_or_two_observation": { "total": 98.76019977489227, "count": 505448, "is_parallel": true, "self": 98.76019977489227 } } } } } } } } } } }, "trainer_advance": { "total": 1026.2954363380397, "count": 63182, "self": 3.881703021027988, "children": { "process_trajectory": { "total": 154.36951624900826, "count": 63182, "self": 153.99242839200838, "children": { "RLTrainer._checkpoint": { "total": 0.37708785699987857, "count": 2, "self": 0.37708785699987857 } } }, "_update_policy": { "total": 868.0442170680035, "count": 426, "self": 363.7552467800549, "children": { "TorchPPOOptimizer.update": { "total": 504.2889702879486, "count": 22953, "self": 504.2889702879486 } } } } } } }, "trainer_threads": { "total": 1.4019997252034955e-06, "count": 1, "self": 1.4019997252034955e-06 }, "TrainerController._save_models": { "total": 0.15621422899948811, "count": 1, "self": 0.0034367259995633503, "children": { "RLTrainer._checkpoint": { "total": 0.15277750299992476, "count": 1, "self": 0.15277750299992476 } } } } } } }