{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39236053824424744, "min": 0.3827058970928192, "max": 1.4822663068771362, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11745.705078125, "min": 11524.0400390625, "max": 44966.03125, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5211248397827148, "min": -0.09819754958152771, "max": 0.5211248397827148, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.87271118164062, "min": -23.567411422729492, "max": 144.87271118164062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02311887964606285, "min": 0.005355083383619785, "max": 0.24483950436115265, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.427048683166504, "min": 1.3762564659118652, "max": 58.02696228027344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06983643630196133, "min": 0.0653242770388919, "max": 0.07435685670671298, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.04754654452942, "min": 0.4708470308573799, "max": 1.04754654452942, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015271202188644868, "min": 0.00023681494731808076, "max": 0.015966372598389476, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22906803282967303, "min": 0.00307859431513505, "max": 0.23934331958783636, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.557617480826668e-06, "min": 7.557617480826668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011336426221240002, "min": 0.00011336426221240002, "max": 0.0035083706305431995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251917333333332, "min": 0.10251917333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377876, "min": 1.3886848, "max": 2.5694567999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026166541600000014, "min": 0.00026166541600000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003924981240000002, "min": 0.003924981240000002, "max": 0.11696873431999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011537143029272556, "min": 0.011537143029272556, "max": 0.33288320899009705, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17305713891983032, "min": 0.1630202978849411, "max": 2.3301825523376465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.65432098765433, "min": 351.65432098765433, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28484.0, "min": 15984.0, "max": 32675.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5989505998146387, "min": -1.0000000521540642, "max": 1.5989505998146387, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 129.51499858498573, "min": -31.995601654052734, "max": 129.51499858498573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5989505998146387, "min": -1.0000000521540642, "max": 1.5989505998146387, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 129.51499858498573, "min": -31.995601654052734, "max": 129.51499858498573, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041867791803303626, "min": 0.041867791803303626, "max": 6.0151911694556475, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3912911360675935, "min": 3.3912911360675935, "max": 96.24305871129036, "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": "1749063541", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749065657" }, "total": 2116.0994175670003, "count": 1, "self": 0.47580007099941213, "children": { "run_training.setup": { "total": 0.021503686000414746, "count": 1, "self": 0.021503686000414746 }, "TrainerController.start_learning": { "total": 2115.6021138100004, "count": 1, "self": 1.242544614048711, "children": { "TrainerController._reset_env": { "total": 2.3306072999998833, "count": 1, "self": 2.3306072999998833 }, "TrainerController.advance": { "total": 2111.946607818951, "count": 63721, "self": 1.3214846838950507, "children": { "env_step": { "total": 1448.246128828036, "count": 63721, "self": 1303.2365450211137, "children": { "SubprocessEnvManager._take_step": { "total": 144.2909579539555, "count": 63721, "self": 4.429156917943601, "children": { "TorchPolicy.evaluate": { "total": 139.8618010360119, "count": 62574, "self": 139.8618010360119 } } }, "workers": { "total": 0.7186258529668521, "count": 63721, "self": 0.0, "children": { "worker_root": { "total": 2110.903061126043, "count": 63721, "is_parallel": true, "self": 913.8536061429431, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026446399997439585, "count": 1, "is_parallel": true, "self": 0.0008430829993812949, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018015570003626635, "count": 8, "is_parallel": true, "self": 0.0018015570003626635 } } }, "UnityEnvironment.step": { "total": 0.047654147000230296, "count": 1, "is_parallel": true, "self": 0.0005482270003085432, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046422900004472467, "count": 1, "is_parallel": true, "self": 0.00046422900004472467 }, "communicator.exchange": { "total": 0.04508380800007217, "count": 1, "is_parallel": true, "self": 0.04508380800007217 }, "steps_from_proto": { "total": 0.0015578829998048604, "count": 1, "is_parallel": true, "self": 0.0003290609988653159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012288220009395445, "count": 8, "is_parallel": true, "self": 0.0012288220009395445 } } } } } } }, "UnityEnvironment.step": { "total": 1197.0494549831, "count": 63720, "is_parallel": true, "self": 30.8375219120594, "children": { "UnityEnvironment._generate_step_input": { "total": 22.88696559209393, "count": 63720, "is_parallel": true, "self": 22.88696559209393 }, "communicator.exchange": { "total": 1051.7040153419453, "count": 63720, "is_parallel": true, "self": 1051.7040153419453 }, "steps_from_proto": { "total": 91.6209521370015, "count": 63720, "is_parallel": true, "self": 18.01695135887394, "children": { "_process_rank_one_or_two_observation": { "total": 73.60400077812756, "count": 509760, "is_parallel": true, "self": 73.60400077812756 } } } } } } } } } } }, "trainer_advance": { "total": 662.3789943070201, "count": 63721, "self": 2.5135267361174556, "children": { "process_trajectory": { "total": 124.23077236590552, "count": 63721, "self": 124.04390614290514, "children": { "RLTrainer._checkpoint": { "total": 0.18686622300037925, "count": 2, "self": 0.18686622300037925 } } }, "_update_policy": { "total": 535.6346952049971, "count": 452, "self": 295.88971525502893, "children": { "TorchPPOOptimizer.update": { "total": 239.74497994996818, "count": 22797, "self": 239.74497994996818 } } } } } } }, "trainer_threads": { "total": 9.000004865811206e-07, "count": 1, "self": 9.000004865811206e-07 }, "TrainerController._save_models": { "total": 0.0823531770001864, "count": 1, "self": 0.0012357750001683598, "children": { "RLTrainer._checkpoint": { "total": 0.08111740200001805, "count": 1, "self": 0.08111740200001805 } } } } } } }