{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3595448136329651, "min": 0.3595448136329651, "max": 1.4661388397216797, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10912.904296875, "min": 10912.904296875, "max": 44476.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29917.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29917.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5210235118865967, "min": -0.07468345016241074, "max": 0.5277383923530579, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.3655548095703, "min": -18.073394775390625, "max": 146.18353271484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02280491031706333, "min": 0.00610071187838912, "max": 0.3032050132751465, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.362569808959961, "min": 1.6471922397613525, "max": 72.49739074707031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06565184057431502, "min": 0.0644105072182157, "max": 0.07329705741832193, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9847776086147253, "min": 0.5081404877723537, "max": 1.087365893239621, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017426610338346412, "min": 0.0015867289570978434, "max": 0.017426610338346412, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2613991550751962, "min": 0.01904074748517412, "max": 0.2613991550751962, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.449797516766669e-06, "min": 7.449797516766669e-06, "max": 0.0002952344158742428, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011174696275150003, "min": 0.00011174696275150003, "max": 0.0037589965470011992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248323333333334, "min": 0.10248323333333334, "max": 0.1984114714285714, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372485, "min": 1.3888802999999998, "max": 2.6529988, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002580750100000001, "min": 0.0002580750100000001, "max": 0.009841305995714285, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003871125150000001, "min": 0.003871125150000001, "max": 0.12531458012000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012290147133171558, "min": 0.011752909980714321, "max": 0.5764356255531311, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18435220420360565, "min": 0.16454073786735535, "max": 4.0350494384765625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.0869565217391, "min": 361.0869565217391, "max": 979.4242424242424, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33220.0, "min": 16588.0, "max": 33220.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5954195416491965, "min": -0.8591212637045167, "max": 1.5964559797445934, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.77859783172607, "min": -28.35100170224905, "max": 146.77859783172607, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5954195416491965, "min": -0.8591212637045167, "max": 1.5964559797445934, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.77859783172607, "min": -28.35100170224905, "max": 146.77859783172607, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045713192691081254, "min": 0.045713192691081254, "max": 11.655536637586707, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.205613727579475, "min": 3.619074439717224, "max": 198.144122838974, "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": "1689788632", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689790913" }, "total": 2281.168236367, "count": 1, "self": 0.44165687100075957, "children": { "run_training.setup": { "total": 0.03529606199998625, "count": 1, "self": 0.03529606199998625 }, "TrainerController.start_learning": { "total": 2280.6912834339996, "count": 1, "self": 1.4261590140458793, "children": { "TrainerController._reset_env": { "total": 5.871074727000007, "count": 1, "self": 5.871074727000007 }, "TrainerController.advance": { "total": 2273.302269060953, "count": 63847, "self": 1.4426524839500416, "children": { "env_step": { "total": 1605.6134333479708, "count": 63847, "self": 1495.3196213298957, "children": { "SubprocessEnvManager._take_step": { "total": 109.43681081507856, "count": 63847, "self": 4.68022170508371, "children": { "TorchPolicy.evaluate": { "total": 104.75658910999485, "count": 62562, "self": 104.75658910999485 } } }, "workers": { "total": 0.8570012029966563, "count": 63847, "self": 0.0, "children": { "worker_root": { "total": 2275.3680282339806, "count": 63847, "is_parallel": true, "self": 895.9019146050089, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004629456000003529, "count": 1, "is_parallel": true, "self": 0.0034123339999609925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012171220000425365, "count": 8, "is_parallel": true, "self": 0.0012171220000425365 } } }, "UnityEnvironment.step": { "total": 0.08352185900000109, "count": 1, "is_parallel": true, "self": 0.0005817779999972572, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005023490000155562, "count": 1, "is_parallel": true, "self": 0.0005023490000155562 }, "communicator.exchange": { "total": 0.08053975699999683, "count": 1, "is_parallel": true, "self": 0.08053975699999683 }, "steps_from_proto": { "total": 0.0018979749999914475, "count": 1, "is_parallel": true, "self": 0.0004809479999892119, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014170270000022356, "count": 8, "is_parallel": true, "self": 0.0014170270000022356 } } } } } } }, "UnityEnvironment.step": { "total": 1379.4661136289717, "count": 63846, "is_parallel": true, "self": 34.01450798894962, "children": { "UnityEnvironment._generate_step_input": { "total": 22.56843464001355, "count": 63846, "is_parallel": true, "self": 22.56843464001355 }, "communicator.exchange": { "total": 1221.902205916033, "count": 63846, "is_parallel": true, "self": 1221.902205916033 }, "steps_from_proto": { "total": 100.98096508397558, "count": 63846, "is_parallel": true, "self": 20.33112581580974, "children": { "_process_rank_one_or_two_observation": { "total": 80.64983926816583, "count": 510768, "is_parallel": true, "self": 80.64983926816583 } } } } } } } } } } }, "trainer_advance": { "total": 666.2461832290321, "count": 63847, "self": 2.6640030020254244, "children": { "process_trajectory": { "total": 109.2719784300044, "count": 63847, "self": 109.0680202620043, "children": { "RLTrainer._checkpoint": { "total": 0.20395816800009925, "count": 2, "self": 0.20395816800009925 } } }, "_update_policy": { "total": 554.3102017970023, "count": 457, "self": 361.52002686298243, "children": { "TorchPPOOptimizer.update": { "total": 192.79017493401983, "count": 22767, "self": 192.79017493401983 } } } } } } }, "trainer_threads": { "total": 9.090003914025147e-07, "count": 1, "self": 9.090003914025147e-07 }, "TrainerController._save_models": { "total": 0.09177972299994508, "count": 1, "self": 0.0013904709999223996, "children": { "RLTrainer._checkpoint": { "total": 0.09038925200002268, "count": 1, "self": 0.09038925200002268 } } } } } } }