{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4009186029434204, "min": 0.4009186029434204, "max": 1.5359002351760864, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12091.705078125, "min": 12069.78125, "max": 46593.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49700871109962463, "min": -0.18596918880939484, "max": 0.6004819273948669, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.18038940429688, "min": -44.07469940185547, "max": 169.93638610839844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00869013648480177, "min": -0.0207500122487545, "max": 0.18648554384708405, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.3810973167419434, "min": -5.291253089904785, "max": 44.19707489013672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07120504008933147, "min": 0.06426148936132066, "max": 0.07507825029454832, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9968705612506406, "min": 0.47523211677533295, "max": 1.0684166522987653, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0142123129993533, "min": 0.00022213860091855039, "max": 0.015791618605403023, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1989723819909462, "min": 0.0026656632110226047, "max": 0.23687427908104536, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.36094040352857e-06, "min": 7.36094040352857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010305316564939998, "min": 0.00010305316564939998, "max": 0.0032535302154899992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024536142857143, "min": 0.1024536142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343506000000001, "min": 1.3691136000000002, "max": 2.4010822999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002551160671428572, "min": 0.0002551160671428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035716249400000004, "min": 0.0035716249400000004, "max": 0.108472549, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007260675076395273, "min": 0.007260675076395273, "max": 0.221393421292305, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1016494482755661, "min": 0.1016494482755661, "max": 1.5497539043426514, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.2906976744186, "min": 328.7173913043478, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30555.0, "min": 15984.0, "max": 32753.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.52839998485044, "min": -1.0000000521540642, "max": 1.6710549217986537, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.44239869713783, "min": -32.000001668930054, "max": 152.06599788367748, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.52839998485044, "min": -1.0000000521540642, "max": 1.6710549217986537, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.44239869713783, "min": -32.000001668930054, "max": 152.06599788367748, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026327032251364745, "min": 0.026327032251364745, "max": 4.2774456879124045, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.264124773617368, "min": 2.264124773617368, "max": 68.43913100659847, "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": "1709831333", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709833995" }, "total": 2661.8019585800002, "count": 1, "self": 0.7783968210001149, "children": { "run_training.setup": { "total": 0.0731579570001486, "count": 1, "self": 0.0731579570001486 }, "TrainerController.start_learning": { "total": 2660.950403802, "count": 1, "self": 1.8574105780612626, "children": { "TrainerController._reset_env": { "total": 3.2399899079998704, "count": 1, "self": 3.2399899079998704 }, "TrainerController.advance": { "total": 2655.7528288489384, "count": 63816, "self": 2.0001695729397397, "children": { "env_step": { "total": 1907.6858059719625, "count": 63816, "self": 1734.538467623913, "children": { "SubprocessEnvManager._take_step": { "total": 171.93349397200404, "count": 63816, "self": 6.573610249038893, "children": { "TorchPolicy.evaluate": { "total": 165.35988372296515, "count": 62552, "self": 165.35988372296515 } } }, "workers": { "total": 1.213844376045472, "count": 63816, "self": 0.0, "children": { "worker_root": { "total": 2654.772913142057, "count": 63816, "is_parallel": true, "self": 1082.261114890141, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002600061000066489, "count": 1, "is_parallel": true, "self": 0.0008350330001576367, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017650279999088525, "count": 8, "is_parallel": true, "self": 0.0017650279999088525 } } }, "UnityEnvironment.step": { "total": 0.09167045300000609, "count": 1, "is_parallel": true, "self": 0.000812137000139046, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006196580000050744, "count": 1, "is_parallel": true, "self": 0.0006196580000050744 }, "communicator.exchange": { "total": 0.08808955799986506, "count": 1, "is_parallel": true, "self": 0.08808955799986506 }, "steps_from_proto": { "total": 0.0021490999999969063, "count": 1, "is_parallel": true, "self": 0.0004980419998901198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016510580001067865, "count": 8, "is_parallel": true, "self": 0.0016510580001067865 } } } } } } }, "UnityEnvironment.step": { "total": 1572.511798251916, "count": 63815, "is_parallel": true, "self": 44.60324884595002, "children": { "UnityEnvironment._generate_step_input": { "total": 29.69352303893379, "count": 63815, "is_parallel": true, "self": 29.69352303893379 }, "communicator.exchange": { "total": 1371.70189010799, "count": 63815, "is_parallel": true, "self": 1371.70189010799 }, "steps_from_proto": { "total": 126.51313625904208, "count": 63815, "is_parallel": true, "self": 27.03768581906934, "children": { "_process_rank_one_or_two_observation": { "total": 99.47545043997275, "count": 510520, "is_parallel": true, "self": 99.47545043997275 } } } } } } } } } } }, "trainer_advance": { "total": 746.0668533040362, "count": 63816, "self": 3.592398183036039, "children": { "process_trajectory": { "total": 153.4884845480044, "count": 63816, "self": 153.24790650900445, "children": { "RLTrainer._checkpoint": { "total": 0.24057803899995633, "count": 2, "self": 0.24057803899995633 } } }, "_update_policy": { "total": 588.9859705729957, "count": 441, "self": 340.1780276580273, "children": { "TorchPPOOptimizer.update": { "total": 248.8079429149684, "count": 22863, "self": 248.8079429149684 } } } } } } }, "trainer_threads": { "total": 1.1500001164677087e-06, "count": 1, "self": 1.1500001164677087e-06 }, "TrainerController._save_models": { "total": 0.1001733170000989, "count": 1, "self": 0.001498996000009356, "children": { "RLTrainer._checkpoint": { "total": 0.09867432100008955, "count": 1, "self": 0.09867432100008955 } } } } } } }