{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.780318558216095, "min": 0.6669133305549622, "max": 1.498272180557251, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 23659.2578125, "min": 20050.08203125, "max": 45451.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010754618793725967, "min": -0.04070800542831421, "max": 0.014654398895800114, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -2.613372325897217, "min": -9.851337432861328, "max": 3.473092555999756, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004297743085771799, "min": 0.0016020304756239057, "max": 0.2212199717760086, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.044351577758789, "min": 0.3876913785934448, "max": 52.429134368896484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06650934721806598, "min": 0.06525298484172691, "max": 0.07321116683115014, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9976402082709896, "min": 0.4990789892502201, "max": 1.0094838537196793, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0019392265049970056, "min": 7.564541352453372e-05, "max": 0.006132301997119608, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.029088397574955085, "min": 0.0010590357893434722, "max": 0.04445060956385194, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.980270843246667e-06, "min": 4.980270843246667e-06, "max": 0.0001967670873307428, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.47040626487e-05, "min": 7.47040626487e-05, "max": 0.0021733956133023003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249008666666669, "min": 0.10249008666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373513000000003, "min": 1.3691136000000002, "max": 2.3866977, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025875965800000003, "min": 0.00025875965800000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038813948700000002, "min": 0.0038813948700000002, "max": 0.10869110023000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012313524261116982, "min": 0.012313524261116982, "max": 0.5040949583053589, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18470285832881927, "min": 0.17599231004714966, "max": 3.5286645889282227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 910.3333333333334, "min": 910.3333333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30041.0, "min": 15984.0, "max": 33248.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5015941634774208, "min": -1.0000000521540642, "max": -0.3497875430621207, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.054201558232307, "min": -32.000001668930054, "max": -11.193201377987862, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5015941634774208, "min": -1.0000000521540642, "max": -0.3497875430621207, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.054201558232307, "min": -32.000001668930054, "max": -11.193201377987862, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11522512740510352, "min": 0.11522512740510352, "max": 11.000271070748568, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9176543317735195, "min": 3.9176543317735195, "max": 176.00433713197708, "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": "1746596369", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746598390" }, "total": 2021.2400372480001, "count": 1, "self": 0.5318505879999975, "children": { "run_training.setup": { "total": 0.021488262000048053, "count": 1, "self": 0.021488262000048053 }, "TrainerController.start_learning": { "total": 2020.686698398, "count": 1, "self": 1.2790333690297757, "children": { "TrainerController._reset_env": { "total": 2.4231243849999373, "count": 1, "self": 2.4231243849999373 }, "TrainerController.advance": { "total": 2016.9056315389703, "count": 63145, "self": 1.3345297839803152, "children": { "env_step": { "total": 1348.1543681829687, "count": 63145, "self": 1199.0195479290148, "children": { "SubprocessEnvManager._take_step": { "total": 148.38269032794574, "count": 63145, "self": 4.52968514194481, "children": { "TorchPolicy.evaluate": { "total": 143.85300518600093, "count": 62564, "self": 143.85300518600093 } } }, "workers": { "total": 0.7521299260081378, "count": 63145, "self": 0.0, "children": { "worker_root": { "total": 2016.3063306128975, "count": 63145, "is_parallel": true, "self": 922.6887429258506, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020497660000273754, "count": 1, "is_parallel": true, "self": 0.0006920130001617508, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013577529998656246, "count": 8, "is_parallel": true, "self": 0.0013577529998656246 } } }, "UnityEnvironment.step": { "total": 0.05041834100006781, "count": 1, "is_parallel": true, "self": 0.0005266210000627325, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004473049998523493, "count": 1, "is_parallel": true, "self": 0.0004473049998523493 }, "communicator.exchange": { "total": 0.04784315400002015, "count": 1, "is_parallel": true, "self": 0.04784315400002015 }, "steps_from_proto": { "total": 0.001601261000132581, "count": 1, "is_parallel": true, "self": 0.00035917500008508796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012420860000474931, "count": 8, "is_parallel": true, "self": 0.0012420860000474931 } } } } } } }, "UnityEnvironment.step": { "total": 1093.6175876870468, "count": 63144, "is_parallel": true, "self": 30.946964149097766, "children": { "UnityEnvironment._generate_step_input": { "total": 22.317222479950033, "count": 63144, "is_parallel": true, "self": 22.317222479950033 }, "communicator.exchange": { "total": 948.2943422869964, "count": 63144, "is_parallel": true, "self": 948.2943422869964 }, "steps_from_proto": { "total": 92.05905877100258, "count": 63144, "is_parallel": true, "self": 18.063992440053426, "children": { "_process_rank_one_or_two_observation": { "total": 73.99506633094916, "count": 505152, "is_parallel": true, "self": 73.99506633094916 } } } } } } } } } } }, "trainer_advance": { "total": 667.4167335720213, "count": 63145, "self": 2.2820343710802717, "children": { "process_trajectory": { "total": 121.68871618994649, "count": 63145, "self": 121.49880862794657, "children": { "RLTrainer._checkpoint": { "total": 0.18990756199991665, "count": 2, "self": 0.18990756199991665 } } }, "_update_policy": { "total": 543.4459830109945, "count": 435, "self": 302.8046139319856, "children": { "TorchPPOOptimizer.update": { "total": 240.64136907900888, "count": 22815, "self": 240.64136907900888 } } } } } } }, "trainer_threads": { "total": 9.039999895321671e-07, "count": 1, "self": 9.039999895321671e-07 }, "TrainerController._save_models": { "total": 0.07890820100010387, "count": 1, "self": 0.0011579060001167818, "children": { "RLTrainer._checkpoint": { "total": 0.07775029499998709, "count": 1, "self": 0.07775029499998709 } } } } } } }