{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2624301016330719, "min": 0.2503872513771057, "max": 1.415424108505249, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 7809.91943359375, "min": 7479.56787109375, "max": 42938.3046875, "count": 66 }, "Pyramids.Step.mean": { "value": 1979972.0, "min": 29952.0, "max": 1979972.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979972.0, "min": 29952.0, "max": 1979972.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5534326434135437, "min": -0.09447427839040756, "max": 0.609072744846344, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.53367614746094, "min": -22.768301010131836, "max": 171.75851440429688, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007547972723841667, "min": -0.015686098486185074, "max": 0.4602912664413452, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.053048610687256, "min": -4.282304763793945, "max": 109.08902740478516, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06894014026203026, "min": 0.06445410102605818, "max": 0.07318553161236367, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9651619636684236, "min": 0.5114105983249891, "max": 1.071707970722962, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011589847809582275, "min": 0.00014715042579319283, "max": 0.01403903107573223, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16225786933415184, "min": 0.0019129555353115067, "max": 0.19952770731013553, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.163312564642856e-06, "min": 5.163312564642856e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.228637590499999e-05, "min": 7.228637590499999e-05, "max": 0.003916468144510649, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10172107142857142, "min": 0.10172107142857142, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4240949999999999, "min": 1.3943424, "max": 2.7054893500000006, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018193503571428573, "min": 0.00018193503571428573, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0025470905000000003, "min": 0.0025470905000000003, "max": 0.13055838606499998, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005576462019234896, "min": 0.005030772648751736, "max": 0.49330100417137146, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07807046920061111, "min": 0.07110690325498581, "max": 3.4531071186065674, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 380.4024390243902, "min": 315.3333333333333, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31193.0, "min": 15984.0, "max": 33271.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4766770876854298, "min": -1.0000000521540642, "max": 1.6416451381419295, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.56419827789068, "min": -31.994401648640633, "max": 152.67299784719944, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4766770876854298, "min": -1.0000000521540642, "max": 1.6416451381419295, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.56419827789068, "min": -31.994401648640633, "max": 152.67299784719944, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021517857894825985, "min": 0.018689367788022212, "max": 9.230703588109463, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7859822052705567, "min": 1.5916997588647064, "max": 147.69125740975142, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684967100", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.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": "1684971533" }, "total": 4432.418219368999, "count": 1, "self": 0.8425378719994114, "children": { "run_training.setup": { "total": 0.06338283100001263, "count": 1, "self": 0.06338283100001263 }, "TrainerController.start_learning": { "total": 4431.512298666, "count": 1, "self": 2.7566301501283306, "children": { "TrainerController._reset_env": { "total": 4.453283148999958, "count": 1, "self": 4.453283148999958 }, "TrainerController.advance": { "total": 4424.144755398872, "count": 128216, "self": 2.9100664849256646, "children": { "env_step": { "total": 3110.9200945618422, "count": 128216, "self": 2885.296031356897, "children": { "SubprocessEnvManager._take_step": { "total": 223.90028392495663, "count": 128216, "self": 9.632010484039938, "children": { "TorchPolicy.evaluate": { "total": 214.2682734409167, "count": 125062, "self": 214.2682734409167 } } }, "workers": { "total": 1.723779279988662, "count": 128216, "self": 0.0, "children": { "worker_root": { "total": 4421.25423290699, "count": 128216, "is_parallel": true, "self": 1768.1496972099885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005590783000002375, "count": 1, "is_parallel": true, "self": 0.003631979999909163, "children": { "_process_rank_one_or_two_observation": { "total": 0.001958803000093212, "count": 8, "is_parallel": true, "self": 0.001958803000093212 } } }, "UnityEnvironment.step": { "total": 0.05145241700006409, "count": 1, "is_parallel": true, "self": 0.0005446720000463756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004964710000194827, "count": 1, "is_parallel": true, "self": 0.0004964710000194827 }, "communicator.exchange": { "total": 0.04862403599997833, "count": 1, "is_parallel": true, "self": 0.04862403599997833 }, "steps_from_proto": { "total": 0.0017872380000198973, "count": 1, "is_parallel": true, "self": 0.000406599000029928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013806389999899693, "count": 8, "is_parallel": true, "self": 0.0013806389999899693 } } } } } } }, "UnityEnvironment.step": { "total": 2653.1045356970017, "count": 128215, "is_parallel": true, "self": 65.44456140778811, "children": { "UnityEnvironment._generate_step_input": { "total": 45.39854862909476, "count": 128215, "is_parallel": true, "self": 45.39854862909476 }, "communicator.exchange": { "total": 2344.497528541059, "count": 128215, "is_parallel": true, "self": 2344.497528541059 }, "steps_from_proto": { "total": 197.7638971190596, "count": 128215, "is_parallel": true, "self": 40.730027855887556, "children": { "_process_rank_one_or_two_observation": { "total": 157.03386926317205, "count": 1025720, "is_parallel": true, "self": 157.03386926317205 } } } } } } } } } } }, "trainer_advance": { "total": 1310.3145943521045, "count": 128216, "self": 5.543658799083914, "children": { "process_trajectory": { "total": 221.8015003650222, "count": 128216, "self": 221.3202100970219, "children": { "RLTrainer._checkpoint": { "total": 0.4812902680002935, "count": 4, "self": 0.4812902680002935 } } }, "_update_policy": { "total": 1082.9694351879982, "count": 923, "self": 696.4650409379615, "children": { "TorchPPOOptimizer.update": { "total": 386.50439425003674, "count": 45549, "self": 386.50439425003674 } } } } } } }, "trainer_threads": { "total": 1.247000000148546e-06, "count": 1, "self": 1.247000000148546e-06 }, "TrainerController._save_models": { "total": 0.15762872100003733, "count": 1, "self": 0.00207904899980349, "children": { "RLTrainer._checkpoint": { "total": 0.15554967200023384, "count": 1, "self": 0.15554967200023384 } } } } } } }