{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5639896988868713, "min": 0.5437616109848022, "max": 1.4248685836791992, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16865.548828125, "min": 16225.845703125, "max": 43224.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42662498354911804, "min": -0.10136526077985764, "max": 0.5101008415222168, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.33549499511719, "min": -24.32766342163086, "max": 139.7676239013672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.3908995985984802, "min": -0.9070993661880493, "max": 0.6894099712371826, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 104.76109313964844, "min": -239.47422790527344, "max": 184.76187133789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06944296214385846, "min": 0.06586443341615303, "max": 0.07352698891279329, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9722014700140185, "min": 0.4854302136260941, "max": 1.0502390304235651, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04569113008118384, "min": 0.0004597290271714257, "max": 0.10072638315785512, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.6396758211365737, "min": 0.005976477353228534, "max": 1.4101693642099717, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.263097579000001e-06, "min": 7.263097579000001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000101683366106, "min": 0.000101683366106, "max": 0.0036324664891779, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.102421, "min": 0.102421, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.433894, "min": 1.3886848, "max": 2.6108221, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025185790000000006, "min": 0.00025185790000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003526010600000001, "min": 0.003526010600000001, "max": 0.12110112779, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007185659371316433, "min": 0.007169574499130249, "max": 0.36034509539604187, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10059922933578491, "min": 0.10059922933578491, "max": 2.5224156379699707, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 405.95, "min": 373.4246575342466, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32476.0, "min": 15984.0, "max": 34139.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5187012421179422, "min": -1.0000000521540642, "max": 1.5443588918814921, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.97739812731743, "min": -29.796801693737507, "max": 119.97739812731743, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5187012421179422, "min": -1.0000000521540642, "max": 1.5443588918814921, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.97739812731743, "min": -29.796801693737507, "max": 119.97739812731743, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03017096373984219, "min": 0.03017096373984219, "max": 7.430791730061173, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.383506135447533, "min": 2.2226977952523157, "max": 118.89266768097878, "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": "1673870993", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673873009" }, "total": 2016.07767922, "count": 1, "self": 0.43650436699999773, "children": { "run_training.setup": { "total": 0.10936031899996124, "count": 1, "self": 0.10936031899996124 }, "TrainerController.start_learning": { "total": 2015.531814534, "count": 1, "self": 1.1783371160065599, "children": { "TrainerController._reset_env": { "total": 6.427757094999947, "count": 1, "self": 6.427757094999947 }, "TrainerController.advance": { "total": 2007.8348136859934, "count": 63623, "self": 1.2097716169835167, "children": { "env_step": { "total": 1340.8602463140317, "count": 63623, "self": 1236.8102956960024, "children": { "SubprocessEnvManager._take_step": { "total": 103.2964568390313, "count": 63623, "self": 4.194368124046946, "children": { "TorchPolicy.evaluate": { "total": 99.10208871498435, "count": 62554, "self": 33.15457880696283, "children": { "TorchPolicy.sample_actions": { "total": 65.94750990802152, "count": 62554, "self": 65.94750990802152 } } } } }, "workers": { "total": 0.7534937789979494, "count": 63623, "self": 0.0, "children": { "worker_root": { "total": 2011.0717664820124, "count": 63623, "is_parallel": true, "self": 871.3645489349676, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001810726000030627, "count": 1, "is_parallel": true, "self": 0.000661765000018022, "children": { "_process_rank_one_or_two_observation": { "total": 0.001148961000012605, "count": 8, "is_parallel": true, "self": 0.001148961000012605 } } }, "UnityEnvironment.step": { "total": 0.043511792999993304, "count": 1, "is_parallel": true, "self": 0.0005441189999828566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005169429999796193, "count": 1, "is_parallel": true, "self": 0.0005169429999796193 }, "communicator.exchange": { "total": 0.04081817799999499, "count": 1, "is_parallel": true, "self": 0.04081817799999499 }, "steps_from_proto": { "total": 0.0016325530000358413, "count": 1, "is_parallel": true, "self": 0.0004567449998376105, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011758080001982307, "count": 8, "is_parallel": true, "self": 0.0011758080001982307 } } } } } } }, "UnityEnvironment.step": { "total": 1139.7072175470448, "count": 63622, "is_parallel": true, "self": 28.137291497931074, "children": { "UnityEnvironment._generate_step_input": { "total": 22.691509166035075, "count": 63622, "is_parallel": true, "self": 22.691509166035075 }, "communicator.exchange": { "total": 988.0952927390064, "count": 63622, "is_parallel": true, "self": 988.0952927390064 }, "steps_from_proto": { "total": 100.7831241440723, "count": 63622, "is_parallel": true, "self": 22.063323585038006, "children": { "_process_rank_one_or_two_observation": { "total": 78.7198005590343, "count": 508976, "is_parallel": true, "self": 78.7198005590343 } } } } } } } } } } }, "trainer_advance": { "total": 665.7647957549782, "count": 63623, "self": 2.3059834529370846, "children": { "process_trajectory": { "total": 143.64358501303423, "count": 63623, "self": 143.45296568503431, "children": { "RLTrainer._checkpoint": { "total": 0.19061932799991155, "count": 2, "self": 0.19061932799991155 } } }, "_update_policy": { "total": 519.8152272890069, "count": 452, "self": 199.47183219298768, "children": { "TorchPPOOptimizer.update": { "total": 320.3433950960192, "count": 22785, "self": 320.3433950960192 } } } } } } }, "trainer_threads": { "total": 9.209998097503558e-07, "count": 1, "self": 9.209998097503558e-07 }, "TrainerController._save_models": { "total": 0.09090571600017938, "count": 1, "self": 0.001462238000385696, "children": { "RLTrainer._checkpoint": { "total": 0.08944347799979369, "count": 1, "self": 0.08944347799979369 } } } } } } }