{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6524809002876282, "min": 0.6524809002876282, "max": 1.4705501794815063, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19250.796875, "min": 19250.796875, "max": 44610.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36446237564086914, "min": -0.09325811266899109, "max": 0.4770409166812897, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.94699096679688, "min": -22.381946563720703, "max": 129.755126953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.16427282989025116, "min": -0.17130430042743683, "max": 0.30304327607154846, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -43.696571350097656, "min": -46.59476852416992, "max": 71.82125854492188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792325928964761, "min": 0.06559769146506288, "max": 0.07268592918913264, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9509256300550665, "min": 0.4991692476435872, "max": 1.0654710608279998, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012431059297588682, "min": 0.0004807890688668602, "max": 0.0199622696269899, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17403483016624155, "min": 0.006250257895269183, "max": 0.27947177477785856, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5667617634928576e-06, "min": 7.5667617634928576e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010593466468890001, "min": 0.00010593466468890001, "max": 0.0035072564309145994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252222142857145, "min": 0.10252222142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353111000000003, "min": 1.3886848, "max": 2.5690854, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026196992071428587, "min": 0.00026196992071428587, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003667578890000002, "min": 0.003667578890000002, "max": 0.11693163146000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00930571649223566, "min": 0.009168436750769615, "max": 0.3567742705345154, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1302800327539444, "min": 0.12835811078548431, "max": 2.497419834136963, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 496.08474576271186, "min": 378.0759493670886, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29269.0, "min": 15984.0, "max": 32282.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.232637262066542, "min": -1.0000000521540642, "max": 1.5459594690724263, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.72559846192598, "min": -30.312001638114452, "max": 122.13079805672169, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.232637262066542, "min": -1.0000000521540642, "max": 1.5459594690724263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.72559846192598, "min": -30.312001638114452, "max": 122.13079805672169, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04779064674936709, "min": 0.03630968288568591, "max": 6.943391263484955, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.819648158212658, "min": 2.819648158212658, "max": 111.09426021575928, "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": "1729237814", "python_version": "3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0]", "command_line_arguments": "/cpfs/user/taishan/miniconda3/envs/ml-agents/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729240461" }, "total": 2647.1359304729995, "count": 1, "self": 0.4285606839985121, "children": { "run_training.setup": { "total": 0.13243761200283188, "count": 1, "self": 0.13243761200283188 }, "TrainerController.start_learning": { "total": 2646.574932176998, "count": 1, "self": 1.0098255497578066, "children": { "TrainerController._reset_env": { "total": 3.1970746160077397, "count": 1, "self": 3.1970746160077397 }, "TrainerController.advance": { "total": 2642.229406590239, "count": 63543, "self": 0.9336012892308645, "children": { "env_step": { "total": 2231.576490821055, "count": 63543, "self": 2129.4908955313294, "children": { "SubprocessEnvManager._take_step": { "total": 101.45009034496616, "count": 63544, "self": 3.7880231003218796, "children": { "TorchPolicy.evaluate": { "total": 97.66206724464428, "count": 62621, "self": 97.66206724464428 } } }, "workers": { "total": 0.6355049447593046, "count": 63543, "self": 0.0, "children": { "worker_root": { "total": 3351.990387798811, "count": 63543, "is_parallel": true, "self": 1298.1987625510228, "children": { "run_training.setup": { "total": 0.13243761200283188, "count": 1, "is_parallel": true, "self": 0.015098709991434589, "children": { "steps_from_proto": { "total": 0.00161097600357607, "count": 1, "is_parallel": true, "self": 0.000494004983920604, "children": { "_process_rank_one_or_two_observation": { "total": 0.001116971019655466, "count": 8, "is_parallel": true, "self": 0.001116971019655466 } } }, "UnityEnvironment.step": { "total": 0.11572792600782122, "count": 1, "is_parallel": true, "self": 0.00012103002518415451, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006946339999558404, "count": 1, "is_parallel": true, "self": 0.0006946339999558404 }, "communicator.exchange": { "total": 0.1140279339888366, "count": 1, "is_parallel": true, "self": 0.1140279339888366 }, "steps_from_proto": { "total": 0.0008843279938446358, "count": 1, "is_parallel": true, "self": 0.00019012900884263217, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006941989850020036, "count": 8, "is_parallel": true, "self": 0.0006941989850020036 } } } } } } }, "UnityEnvironment.step": { "total": 2053.659187635785, "count": 63541, "is_parallel": true, "self": 7.234220153011847, "children": { "UnityEnvironment._generate_step_input": { "total": 34.52307016259874, "count": 63541, "is_parallel": true, "self": 34.52307016259874 }, "communicator.exchange": { "total": 1959.9089433813351, "count": 63541, "is_parallel": true, "self": 1959.9089433813351 }, "steps_from_proto": { "total": 51.99295393883949, "count": 63541, "is_parallel": true, "self": 10.524916169350035, "children": { "_process_rank_one_or_two_observation": { "total": 41.468037769489456, "count": 508328, "is_parallel": true, "self": 41.468037769489456 } } } } }, "TrainerController.start_learning": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "TrainerController._reset_env": { "total": 3.1970746160077397, "count": 1, "is_parallel": true, "self": 3.1970746160077397 }, "TrainerController.advance": { "total": 704.0082399569801, "count": 17445, "is_parallel": true, "self": 0.2507582859834656, "children": { "env_step": { "total": 591.1661858067528, "count": 17445, "is_parallel": true, "self": 561.950506352805, "children": { "SubprocessEnvManager._take_step": { "total": 28.991436835975037, "count": 17446, "is_parallel": true, "self": 1.0435211764706764, "children": { "TorchPolicy.evaluate": { "total": 27.94791565950436, "count": 17357, "is_parallel": true, "self": 27.94791565950436 } } }, "workers": { "total": 0.17297721598879434, "count": 17445, "is_parallel": true, "self": 0.0, "children": { "worker_root": { "total": 707.1044786637358, "count": 17445, "is_parallel": true, "self": 163.69765298755374, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00161097600357607, "count": 1, "is_parallel": true, "self": 0.000494004983920604, "children": { "_process_rank_one_or_two_observation": { "total": 0.001116971019655466, "count": 8, "is_parallel": true, "self": 0.001116971019655466 } } }, "UnityEnvironment.step": { "total": 0.11572792600782122, "count": 1, "is_parallel": true, "self": 0.00012103002518415451, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006946339999558404, "count": 1, "is_parallel": true, "self": 0.0006946339999558404 }, "communicator.exchange": { "total": 0.1140279339888366, "count": 1, "is_parallel": true, "self": 0.1140279339888366 }, "steps_from_proto": { "total": 0.0008843279938446358, "count": 1, "is_parallel": true, "self": 0.00019012900884263217, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006941989850020036, "count": 8, "is_parallel": true, "self": 0.0006941989850020036 } } } } } } }, "UnityEnvironment.step": { "total": 543.406825676182, "count": 17444, "is_parallel": true, "self": 1.8957679864397505, "children": { "UnityEnvironment._generate_step_input": { "total": 9.49863564989937, "count": 17444, "is_parallel": true, "self": 9.49863564989937 }, "communicator.exchange": { "total": 517.8208545059751, "count": 17444, "is_parallel": true, "self": 517.8208545059751 }, "steps_from_proto": { "total": 14.191567533867783, "count": 17444, "is_parallel": true, "self": 2.828539321257267, "children": { "_process_rank_one_or_two_observation": { "total": 11.363028212610516, "count": 139552, "is_parallel": true, "self": 11.363028212610516 } } } } } } } } }, "steps_from_proto": { "total": 0.0015358179953182116, "count": 1, "is_parallel": true, "self": 0.0004476649919524789, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010881530033657327, "count": 8, "is_parallel": true, "self": 0.0010881530033657327 } } }, "UnityEnvironment.step": { "total": 0.04972958398866467, "count": 1, "is_parallel": true, "self": 0.00012414799130056053, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006500849995063618, "count": 1, "is_parallel": true, "self": 0.0006500849995063618 }, "communicator.exchange": { "total": 0.048106713002198376, "count": 1, "is_parallel": true, "self": 0.048106713002198376 }, "steps_from_proto": { "total": 0.0008486379956593737, "count": 1, "is_parallel": true, "self": 0.00018992897821590304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006587090174434707, "count": 8, "is_parallel": true, "self": 0.0006587090174434707 } } } } } } }, "trainer_advance": { "total": 112.59129586424388, "count": 17445, "is_parallel": true, "self": 0.40781646892719436, "children": { "process_trajectory": { "total": 21.065620380381006, "count": 17445, "is_parallel": true, "self": 21.065620380381006 }, "_update_policy": { "total": 91.11785901493568, "count": 110, "is_parallel": true, "self": 50.792928515482345, "children": { "TorchPPOOptimizer.update": { "total": 40.32493049945333, "count": 6330, "is_parallel": true, "self": 40.32493049945333 } } } } } } } } } } } } } } }, "trainer_advance": { "total": 409.719314479953, "count": 63543, "self": 1.7765321361948736, "children": { "process_trajectory": { "total": 80.34752689780726, "count": 63543, "self": 80.0011609288049, "children": { "RLTrainer._checkpoint": { "total": 0.34636596900236327, "count": 2, "self": 0.34636596900236327 } } }, "_update_policy": { "total": 327.5952554459509, "count": 442, "self": 183.68929388972174, "children": { "TorchPPOOptimizer.update": { "total": 143.90596155622916, "count": 22815, "self": 143.90596155622916 } } } } } } }, "trainer_threads": { "total": 9.469949873164296e-07, "count": 1, "self": 9.469949873164296e-07 }, "TrainerController._save_models": { "total": 0.13862447399878874, "count": 1, "self": 0.017148501006886363, "children": { "RLTrainer._checkpoint": { "total": 0.12147597299190238, "count": 1, "self": 0.12147597299190238 } } } } } } }