{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5360606908798218, "min": 0.5360606908798218, "max": 1.3728686571121216, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15927.435546875, "min": 15927.435546875, "max": 41647.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29951.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29951.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6375973224639893, "min": -0.10701658576726913, "max": 0.6375973224639893, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 181.71524047851562, "min": -25.790996551513672, "max": 181.71524047851562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.11850735545158386, "min": -0.019594412297010422, "max": 0.3461554944515228, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.77459716796875, "min": -5.192519187927246, "max": 83.07731628417969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06710760621107603, "min": 0.06511155605327629, "max": 0.07524435755320798, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9395064869550644, "min": 0.6019548604256638, "max": 1.0148812293839142, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015408437557641057, "min": 9.127378901801838e-05, "max": 0.01610930739097814, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2157181258069748, "min": 0.0012778330462522574, "max": 0.22553030347369393, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.255447581550005e-06, "min": 7.255447581550005e-06, "max": 0.0002952058890980375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010157626614170007, "min": 0.00010157626614170007, "max": 0.0035077472307509998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241845000000001, "min": 0.10241845000000001, "max": 0.19840196249999997, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338583, "min": 1.4338583, "max": 2.569249, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002516031550000002, "min": 0.0002516031550000002, "max": 0.00984035605375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035224441700000024, "min": 0.0035224441700000024, "max": 0.11694797509999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011999146081507206, "min": 0.011913491412997246, "max": 0.4316900968551636, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16798804700374603, "min": 0.16678887605667114, "max": 3.4535207748413086, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.90625, "min": 310.90625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29847.0, "min": 15983.0, "max": 32883.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6265708202651392, "min": -1.0000000521540642, "max": 1.6818171880578483, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.15079874545336, "min": -32.000001668930054, "max": 166.48999809473753, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6265708202651392, "min": -1.0000000521540642, "max": 1.6818171880578483, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.15079874545336, "min": -32.000001668930054, "max": 166.48999809473753, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03878641929183383, "min": 0.03878641929183383, "max": 7.789232974871993, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.723496252016048, "min": 3.6395793275296455, "max": 124.62772759795189, "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": "1735928393", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/home/ubuntu/unit_5/.env/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+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1735930160" }, "total": 1766.3443184120001, "count": 1, "self": 0.9882328430003327, "children": { "run_training.setup": { "total": 0.014750370999990992, "count": 1, "self": 0.014750370999990992 }, "TrainerController.start_learning": { "total": 1765.3413351979998, "count": 1, "self": 1.2962511280206854, "children": { "TrainerController._reset_env": { "total": 1.3722177240001656, "count": 1, "self": 1.3722177240001656 }, "TrainerController.advance": { "total": 1762.6242180079794, "count": 63698, "self": 1.2372538119420824, "children": { "env_step": { "total": 1154.2167012490122, "count": 63698, "self": 1063.93974330505, "children": { "SubprocessEnvManager._take_step": { "total": 89.50726983799268, "count": 63698, "self": 3.672276922025958, "children": { "TorchPolicy.evaluate": { "total": 85.83499291596672, "count": 62566, "self": 85.83499291596672 } } }, "workers": { "total": 0.7696881059696352, "count": 63698, "self": 0.0, "children": { "worker_root": { "total": 1762.9259412970118, "count": 63698, "is_parallel": true, "self": 780.285789576008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013524559999495978, "count": 1, "is_parallel": true, "self": 0.0005591369995272544, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007933190004223434, "count": 8, "is_parallel": true, "self": 0.0007933190004223434 } } }, "UnityEnvironment.step": { "total": 0.04354331800004729, "count": 1, "is_parallel": true, "self": 0.0002454799996485235, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023227700012284913, "count": 1, "is_parallel": true, "self": 0.00023227700012284913 }, "communicator.exchange": { "total": 0.04217320899988408, "count": 1, "is_parallel": true, "self": 0.04217320899988408 }, "steps_from_proto": { "total": 0.0008923520003918384, "count": 1, "is_parallel": true, "self": 0.0002761410005405196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006162109998513188, "count": 8, "is_parallel": true, "self": 0.0006162109998513188 } } } } } } }, "UnityEnvironment.step": { "total": 982.6401517210038, "count": 63697, "is_parallel": true, "self": 15.334219500955442, "children": { "UnityEnvironment._generate_step_input": { "total": 12.523818959964046, "count": 63697, "is_parallel": true, "self": 12.523818959964046 }, "communicator.exchange": { "total": 907.0659889330918, "count": 63697, "is_parallel": true, "self": 907.0659889330918 }, "steps_from_proto": { "total": 47.716124326992485, "count": 63697, "is_parallel": true, "self": 11.441222403930624, "children": { "_process_rank_one_or_two_observation": { "total": 36.27490192306186, "count": 509576, "is_parallel": true, "self": 36.27490192306186 } } } } } } } } } } }, "trainer_advance": { "total": 607.1702629470251, "count": 63698, "self": 2.199733846025083, "children": { "process_trajectory": { "total": 90.25426579800387, "count": 63698, "self": 90.14351978800369, "children": { "RLTrainer._checkpoint": { "total": 0.11074601000018447, "count": 2, "self": 0.11074601000018447 } } }, "_update_policy": { "total": 514.7162633029961, "count": 450, "self": 206.63335311195306, "children": { "TorchPPOOptimizer.update": { "total": 308.0829101910431, "count": 22758, "self": 308.0829101910431 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.048647391999566025, "count": 1, "self": 0.0010855629993784532, "children": { "RLTrainer._checkpoint": { "total": 0.04756182900018757, "count": 1, "self": 0.04756182900018757 } } } } } } }