{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7978783249855042, "min": 0.7978783249855042, "max": 1.5030097961425781, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 24012.9453125, "min": 24012.9453125, "max": 45595.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08442693948745728, "min": -0.11093426495790482, "max": 0.13142763078212738, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 21.022308349609375, "min": -26.624223709106445, "max": 31.148347854614258, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0022148864809423685, "min": 0.0018094871193170547, "max": 0.11095685511827469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.551506757736206, "min": 0.43608638644218445, "max": 26.29677391052246, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06769266302165175, "min": 0.06363532833946758, "max": 0.07290189071520589, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9476972823031246, "min": 0.48211918071871784, "max": 1.0206264700128824, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006273652748859605, "min": 9.22956137526681e-05, "max": 0.007606271885880892, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08783113848403447, "min": 0.0012921385925373534, "max": 0.08783113848403447, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.433711807842856e-06, "min": 7.433711807842856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010407196530979999, "min": 0.00010407196530979999, "max": 0.003224579525140199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247787142857144, "min": 0.10247787142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346902000000001, "min": 1.3691136000000002, "max": 2.3593977999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025753935571428576, "min": 0.00025753935571428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036055509800000003, "min": 0.0036055509800000003, "max": 0.10749849401999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012230935506522655, "min": 0.012230935506522655, "max": 0.4239945113658905, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17123310267925262, "min": 0.17123310267925262, "max": 2.967961549758911, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 807.6, "min": 807.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28266.0, "min": 15984.0, "max": 32532.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.2777999643768583, "min": -1.0000000521540642, "max": 0.2777999643768583, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 9.72299875319004, "min": -32.000001668930054, "max": 9.72299875319004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.2777999643768583, "min": -1.0000000521540642, "max": 0.2777999643768583, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 9.72299875319004, "min": -32.000001668930054, "max": 9.72299875319004, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10359016883386565, "min": 0.10359016883386565, "max": 8.987659143283963, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.625655909185298, "min": 3.625655909185298, "max": 143.8025462925434, "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": "1740855939", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740858119" }, "total": 2180.269202967, "count": 1, "self": 0.4880753930001447, "children": { "run_training.setup": { "total": 0.020924384999943868, "count": 1, "self": 0.020924384999943868 }, "TrainerController.start_learning": { "total": 2179.760203189, "count": 1, "self": 1.4958217150328892, "children": { "TrainerController._reset_env": { "total": 2.12679454299996, "count": 1, "self": 2.12679454299996 }, "TrainerController.advance": { "total": 2176.0466050619675, "count": 63194, "self": 1.5953910110797551, "children": { "env_step": { "total": 1494.3086352009914, "count": 63194, "self": 1330.4030968470252, "children": { "SubprocessEnvManager._take_step": { "total": 163.04657656995778, "count": 63194, "self": 5.000335806107159, "children": { "TorchPolicy.evaluate": { "total": 158.04624076385062, "count": 62565, "self": 158.04624076385062 } } }, "workers": { "total": 0.8589617840084429, "count": 63194, "self": 0.0, "children": { "worker_root": { "total": 2174.322043326962, "count": 63194, "is_parallel": true, "self": 961.8532529219756, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020378310000523925, "count": 1, "is_parallel": true, "self": 0.0006540059998769721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013838250001754204, "count": 8, "is_parallel": true, "self": 0.0013838250001754204 } } }, "UnityEnvironment.step": { "total": 0.04738501399970119, "count": 1, "is_parallel": true, "self": 0.0005109519993311551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004492939997362555, "count": 1, "is_parallel": true, "self": 0.0004492939997362555 }, "communicator.exchange": { "total": 0.044696008000300935, "count": 1, "is_parallel": true, "self": 0.044696008000300935 }, "steps_from_proto": { "total": 0.0017287600003328407, "count": 1, "is_parallel": true, "self": 0.0003495570003906323, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013792029999422084, "count": 8, "is_parallel": true, "self": 0.0013792029999422084 } } } } } } }, "UnityEnvironment.step": { "total": 1212.4687904049865, "count": 63193, "is_parallel": true, "self": 32.32208608105384, "children": { "UnityEnvironment._generate_step_input": { "total": 23.588267821843147, "count": 63193, "is_parallel": true, "self": 23.588267821843147 }, "communicator.exchange": { "total": 1057.015495350082, "count": 63193, "is_parallel": true, "self": 1057.015495350082 }, "steps_from_proto": { "total": 99.54294115200764, "count": 63193, "is_parallel": true, "self": 20.61858255512834, "children": { "_process_rank_one_or_two_observation": { "total": 78.9243585968793, "count": 505544, "is_parallel": true, "self": 78.9243585968793 } } } } } } } } } } }, "trainer_advance": { "total": 680.1425788498964, "count": 63194, "self": 2.6798844259806174, "children": { "process_trajectory": { "total": 127.74681467290975, "count": 63194, "self": 127.53814221090943, "children": { "RLTrainer._checkpoint": { "total": 0.2086724620003224, "count": 2, "self": 0.2086724620003224 } } }, "_update_policy": { "total": 549.715879751006, "count": 433, "self": 304.2269799759597, "children": { "TorchPPOOptimizer.update": { "total": 245.48889977504632, "count": 22851, "self": 245.48889977504632 } } } } } } }, "trainer_threads": { "total": 9.049999789567664e-07, "count": 1, "self": 9.049999789567664e-07 }, "TrainerController._save_models": { "total": 0.09098096399975475, "count": 1, "self": 0.0012814729998353869, "children": { "RLTrainer._checkpoint": { "total": 0.08969949099991936, "count": 1, "self": 0.08969949099991936 } } } } } } }