{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3880952000617981, "min": 0.3812307119369507, "max": 1.4592605829238892, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11649.0654296875, "min": 11461.3203125, "max": 44268.12890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5611673593521118, "min": -0.06251580268144608, "max": 0.669075071811676, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.00453186035156, "min": -15.128824234008789, "max": 191.35546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016362611204385757, "min": 0.0005553122609853745, "max": 0.2754676640033722, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.5488057136535645, "min": 0.1477130651473999, "max": 66.66317749023438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06826502393681037, "min": 0.06449858722737103, "max": 0.0735730835933579, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9557103351153452, "min": 0.5035690260002652, "max": 1.1035962539003685, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016163492445339624, "min": 0.0016161308012807892, "max": 0.016163492445339624, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22628889423475473, "min": 0.01939356961536947, "max": 0.23944672587066296, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.397947534050003e-06, "min": 7.397947534050003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010357126547670003, "min": 0.00010357126547670003, "max": 0.0037578697473768, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246595000000001, "min": 0.10246595000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345233000000002, "min": 1.3886848, "max": 2.6526232000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025634840500000016, "min": 0.00025634840500000016, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035888776700000024, "min": 0.0035888776700000024, "max": 0.12527705768, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00968009140342474, "min": 0.00957552995532751, "max": 0.4069597125053406, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1355212777853012, "min": 0.13405741751194, "max": 2.8487179279327393, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.6741573033708, "min": 288.0521739130435, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27917.0, "min": 15984.0, "max": 33126.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.641373018870193, "min": -1.0000000521540642, "max": 1.6543356985563324, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.08219867944717, "min": -26.452601701021194, "max": 188.87179896980524, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.641373018870193, "min": -1.0000000521540642, "max": 1.6543356985563324, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.08219867944717, "min": -26.452601701021194, "max": 188.87179896980524, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03156256028552398, "min": 0.029223396605812014, "max": 8.309522284194827, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8090678654116346, "min": 2.8090678654116346, "max": 132.95235654711723, "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": "1679406948", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679409318" }, "total": 2370.2493223170004, "count": 1, "self": 0.42519741400019484, "children": { "run_training.setup": { "total": 0.10605157300005885, "count": 1, "self": 0.10605157300005885 }, "TrainerController.start_learning": { "total": 2369.71807333, "count": 1, "self": 1.5976280500508437, "children": { "TrainerController._reset_env": { "total": 6.3837448099998255, "count": 1, "self": 6.3837448099998255 }, "TrainerController.advance": { "total": 2361.6359534379503, "count": 64167, "self": 1.645916338913139, "children": { "env_step": { "total": 1705.6051230060586, "count": 64167, "self": 1584.7397345941388, "children": { "SubprocessEnvManager._take_step": { "total": 119.92590189503858, "count": 64167, "self": 5.135566347056056, "children": { "TorchPolicy.evaluate": { "total": 114.79033554798252, "count": 62559, "self": 114.79033554798252 } } }, "workers": { "total": 0.9394865168812885, "count": 64167, "self": 0.0, "children": { "worker_root": { "total": 2363.82101343199, "count": 64167, "is_parallel": true, "self": 910.1459580090063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020051530000273488, "count": 1, "is_parallel": true, "self": 0.0006681589998152049, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013369940002121439, "count": 8, "is_parallel": true, "self": 0.0013369940002121439 } } }, "UnityEnvironment.step": { "total": 0.08751957899994522, "count": 1, "is_parallel": true, "self": 0.000468622000198593, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047353299987662467, "count": 1, "is_parallel": true, "self": 0.00047353299987662467 }, "communicator.exchange": { "total": 0.08480651900003977, "count": 1, "is_parallel": true, "self": 0.08480651900003977 }, "steps_from_proto": { "total": 0.0017709049998302362, "count": 1, "is_parallel": true, "self": 0.0004294999996545812, "children": { "_process_rank_one_or_two_observation": { "total": 0.001341405000175655, "count": 8, "is_parallel": true, "self": 0.001341405000175655 } } } } } } }, "UnityEnvironment.step": { "total": 1453.6750554229839, "count": 64166, "is_parallel": true, "self": 32.70420477190237, "children": { "UnityEnvironment._generate_step_input": { "total": 25.664250957035392, "count": 64166, "is_parallel": true, "self": 25.664250957035392 }, "communicator.exchange": { "total": 1293.0836898080372, "count": 64166, "is_parallel": true, "self": 1293.0836898080372 }, "steps_from_proto": { "total": 102.22290988600889, "count": 64166, "is_parallel": true, "self": 22.74839981287346, "children": { "_process_rank_one_or_two_observation": { "total": 79.47451007313543, "count": 513328, "is_parallel": true, "self": 79.47451007313543 } } } } } } } } } } }, "trainer_advance": { "total": 654.3849140929788, "count": 64167, "self": 2.909226273994591, "children": { "process_trajectory": { "total": 128.16548329398324, "count": 64167, "self": 127.95591064098312, "children": { "RLTrainer._checkpoint": { "total": 0.20957265300012295, "count": 2, "self": 0.20957265300012295 } } }, "_update_policy": { "total": 523.3102045250009, "count": 458, "self": 332.91609585001925, "children": { "TorchPPOOptimizer.update": { "total": 190.39410867498168, "count": 22836, "self": 190.39410867498168 } } } } } } }, "trainer_threads": { "total": 1.0129997463081963e-06, "count": 1, "self": 1.0129997463081963e-06 }, "TrainerController._save_models": { "total": 0.10074601899941626, "count": 1, "self": 0.0014489679997495841, "children": { "RLTrainer._checkpoint": { "total": 0.09929705099966668, "count": 1, "self": 0.09929705099966668 } } } } } } }