{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5151756405830383, "min": 0.4937754273414612, "max": 1.4677432775497437, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15430.541015625, "min": 14639.4541015625, "max": 44525.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29977.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29977.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5688852071762085, "min": -0.09507118165493011, "max": 0.5703299641609192, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.85675048828125, "min": -22.912155151367188, "max": 159.85675048828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02333887480199337, "min": -0.01473192311823368, "max": 0.4760156273841858, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.558223724365234, "min": -3.8597638607025146, "max": 113.29171752929688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06720001774928754, "min": 0.06545600569000455, "max": 0.07301168280548631, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9408002484900254, "min": 0.476887958406286, "max": 1.0701088743945173, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013673518291657926, "min": 0.00012041838231152276, "max": 0.013749681078194294, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19142925608321096, "min": 0.0015654389700497959, "max": 0.19472646024951246, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4197618124928585e-06, "min": 7.4197618124928585e-06, "max": 0.00029523733015898577, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010387666537490001, "min": 0.00010387666537490001, "max": 0.0036088401970533, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247322142857143, "min": 0.10247322142857143, "max": 0.19841244285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346251, "min": 1.3888871, "max": 2.5281381, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025707482071428585, "min": 0.00025707482071428585, "max": 0.009841403041428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035990474900000017, "min": 0.0035990474900000017, "max": 0.12030437533, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005797781050205231, "min": 0.005702413152903318, "max": 0.30150943994522095, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08116893470287323, "min": 0.07983378320932388, "max": 2.1105661392211914, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.031914893617, "min": 327.26666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32339.0, "min": 16648.0, "max": 33206.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.570829764484091, "min": -0.999880051612854, "max": 1.5708743967982226, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.65799786150455, "min": -31.995601654052734, "max": 147.65799786150455, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.570829764484091, "min": -0.999880051612854, "max": 1.5708743967982226, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.65799786150455, "min": -31.995601654052734, "max": 147.65799786150455, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02064255455247513, "min": 0.02014948305213145, "max": 5.967881978434675, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9404001279326621, "min": 1.6609239851823077, "max": 101.45399363338947, "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": "1772231955", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1772234157" }, "total": 2202.2745240430004, "count": 1, "self": 0.5804008870009056, "children": { "run_training.setup": { "total": 0.023337999999966996, "count": 1, "self": 0.023337999999966996 }, "TrainerController.start_learning": { "total": 2201.6707851559995, "count": 1, "self": 1.2881512870003462, "children": { "TrainerController._reset_env": { "total": 2.092294653999943, "count": 1, "self": 2.092294653999943 }, "TrainerController.advance": { "total": 2198.213185983999, "count": 63846, "self": 1.3452456050190449, "children": { "env_step": { "total": 1541.093910479035, "count": 63846, "self": 1389.3073577249327, "children": { "SubprocessEnvManager._take_step": { "total": 150.99965603505893, "count": 63846, "self": 4.66069451009821, "children": { "TorchPolicy.evaluate": { "total": 146.33896152496072, "count": 62537, "self": 146.33896152496072 } } }, "workers": { "total": 0.7868967190433978, "count": 63846, "self": 0.0, "children": { "worker_root": { "total": 2194.312192937073, "count": 63846, "is_parallel": true, "self": 922.394727362089, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018097529998613027, "count": 1, "is_parallel": true, "self": 0.0005509339998752694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012588189999860333, "count": 8, "is_parallel": true, "self": 0.0012588189999860333 } } }, "UnityEnvironment.step": { "total": 0.04935867499989399, "count": 1, "is_parallel": true, "self": 0.0005379489996357734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005064480001237825, "count": 1, "is_parallel": true, "self": 0.0005064480001237825 }, "communicator.exchange": { "total": 0.04668886000013117, "count": 1, "is_parallel": true, "self": 0.04668886000013117 }, "steps_from_proto": { "total": 0.0016254180000032648, "count": 1, "is_parallel": true, "self": 0.00036965099980079685, "children": { "_process_rank_one_or_two_observation": { "total": 0.001255767000202468, "count": 8, "is_parallel": true, "self": 0.001255767000202468 } } } } } } }, "UnityEnvironment.step": { "total": 1271.9174655749841, "count": 63845, "is_parallel": true, "self": 34.32030016775525, "children": { "UnityEnvironment._generate_step_input": { "total": 23.701151613018055, "count": 63845, "is_parallel": true, "self": 23.701151613018055 }, "communicator.exchange": { "total": 1104.6521258711477, "count": 63845, "is_parallel": true, "self": 1104.6521258711477 }, "steps_from_proto": { "total": 109.24388792306308, "count": 63845, "is_parallel": true, "self": 22.73648192996734, "children": { "_process_rank_one_or_two_observation": { "total": 86.50740599309574, "count": 510760, "is_parallel": true, "self": 86.50740599309574 } } } } } } } } } } }, "trainer_advance": { "total": 655.7740298999454, "count": 63846, "self": 2.5770989599429868, "children": { "process_trajectory": { "total": 125.98632838600633, "count": 63846, "self": 125.8096104550059, "children": { "RLTrainer._checkpoint": { "total": 0.17671793100043942, "count": 2, "self": 0.17671793100043942 } } }, "_update_policy": { "total": 527.2106025539961, "count": 455, "self": 291.4364088920104, "children": { "TorchPPOOptimizer.update": { "total": 235.7741936619857, "count": 22782, "self": 235.7741936619857 } } } } } } }, "trainer_threads": { "total": 9.030000001075678e-07, "count": 1, "self": 9.030000001075678e-07 }, "TrainerController._save_models": { "total": 0.07715232800001104, "count": 1, "self": 0.001103937000152655, "children": { "RLTrainer._checkpoint": { "total": 0.07604839099985838, "count": 1, "self": 0.07604839099985838 } } } } } } }