{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36364200711250305, "min": 0.36364200711250305, "max": 1.3728371858596802, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10816.16796875, "min": 10816.16796875, "max": 41646.390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6208563446998596, "min": -0.17634855210781097, "max": 0.6208563446998596, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.18577575683594, "min": -41.79460525512695, "max": 178.18577575683594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013626371510326862, "min": -0.027822215110063553, "max": 0.4387395977973938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.910768508911133, "min": -7.577263355255127, "max": 103.98128509521484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06691639475147461, "min": 0.06555546049068063, "max": 0.0759718325962999, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9368295265206446, "min": 0.5157030166368316, "max": 1.0673427187042155, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015757295535184398, "min": 0.0006398104458880431, "max": 0.01641859239766962, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22060213749258156, "min": 0.007677725350656517, "max": 0.23230095482579724, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.533868917314286e-06, "min": 7.533868917314286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010547416484240001, "min": 0.00010547416484240001, "max": 0.0035081942306019994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251125714285715, "min": 0.10251125714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351576000000001, "min": 1.3886848, "max": 2.5693980000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002608745885714286, "min": 0.0002608745885714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00365224424, "min": 0.00365224424, "max": 0.1169628602, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010614538565278053, "min": 0.010613742284476757, "max": 0.5353301167488098, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14860354363918304, "min": 0.14859239757061005, "max": 3.7473106384277344, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.6509433962264, "min": 282.6509433962264, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29961.0, "min": 15984.0, "max": 32733.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6796075322155684, "min": -1.0000000521540642, "max": 1.6796075322155684, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.03839841485023, "min": -30.76480170339346, "max": 178.03839841485023, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6796075322155684, "min": -1.0000000521540642, "max": 1.6796075322155684, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.03839841485023, "min": -30.76480170339346, "max": 178.03839841485023, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03063582830344665, "min": 0.03063582830344665, "max": 11.312382686883211, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.247397800165345, "min": 3.176493398263119, "max": 180.99812299013138, "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": "1746389626", "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": "1746392072" }, "total": 2446.1465785089995, "count": 1, "self": 0.589654671999142, "children": { "run_training.setup": { "total": 0.021081401000174083, "count": 1, "self": 0.021081401000174083 }, "TrainerController.start_learning": { "total": 2445.535842436, "count": 1, "self": 1.6801847089809598, "children": { "TrainerController._reset_env": { "total": 2.299448016000042, "count": 1, "self": 2.299448016000042 }, "TrainerController.advance": { "total": 2441.454463265019, "count": 64018, "self": 1.6988758789789244, "children": { "env_step": { "total": 1745.0376577569712, "count": 64018, "self": 1569.8189355540708, "children": { "SubprocessEnvManager._take_step": { "total": 174.2510219958897, "count": 64018, "self": 5.2638812378772855, "children": { "TorchPolicy.evaluate": { "total": 168.9871407580124, "count": 62563, "self": 168.9871407580124 } } }, "workers": { "total": 0.9677002070106937, "count": 64018, "self": 0.0, "children": { "worker_root": { "total": 2439.5056493660745, "count": 64018, "is_parallel": true, "self": 998.0195492090181, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00272710899980666, "count": 1, "is_parallel": true, "self": 0.000864294999928461, "children": { "_process_rank_one_or_two_observation": { "total": 0.001862813999878199, "count": 8, "is_parallel": true, "self": 0.001862813999878199 } } }, "UnityEnvironment.step": { "total": 0.07754951399988386, "count": 1, "is_parallel": true, "self": 0.0005398840000907512, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004618009998011985, "count": 1, "is_parallel": true, "self": 0.0004618009998011985 }, "communicator.exchange": { "total": 0.07481517099995472, "count": 1, "is_parallel": true, "self": 0.07481517099995472 }, "steps_from_proto": { "total": 0.0017326580000371905, "count": 1, "is_parallel": true, "self": 0.0003678880002553342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013647699997818563, "count": 8, "is_parallel": true, "self": 0.0013647699997818563 } } } } } } }, "UnityEnvironment.step": { "total": 1441.4861001570564, "count": 64017, "is_parallel": true, "self": 33.29589449500213, "children": { "UnityEnvironment._generate_step_input": { "total": 24.041546374058953, "count": 64017, "is_parallel": true, "self": 24.041546374058953 }, "communicator.exchange": { "total": 1280.791484435022, "count": 64017, "is_parallel": true, "self": 1280.791484435022 }, "steps_from_proto": { "total": 103.35717485297323, "count": 64017, "is_parallel": true, "self": 21.94392577315216, "children": { "_process_rank_one_or_two_observation": { "total": 81.41324907982107, "count": 512136, "is_parallel": true, "self": 81.41324907982107 } } } } } } } } } } }, "trainer_advance": { "total": 694.717929629069, "count": 64018, "self": 3.2868444970681594, "children": { "process_trajectory": { "total": 135.5165216779926, "count": 64018, "self": 135.30520367999247, "children": { "RLTrainer._checkpoint": { "total": 0.2113179980001405, "count": 2, "self": 0.2113179980001405 } } }, "_update_policy": { "total": 555.9145634540082, "count": 452, "self": 308.9538338599684, "children": { "TorchPPOOptimizer.update": { "total": 246.96072959403978, "count": 22821, "self": 246.96072959403978 } } } } } } }, "trainer_threads": { "total": 1.0670000847312622e-06, "count": 1, "self": 1.0670000847312622e-06 }, "TrainerController._save_models": { "total": 0.10174537900002179, "count": 1, "self": 0.0014609360005124472, "children": { "RLTrainer._checkpoint": { "total": 0.10028444299950934, "count": 1, "self": 0.10028444299950934 } } } } } } }