{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46295198798179626, "min": 0.4524446129798889, "max": 1.4660159349441528, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13895.966796875, "min": 13587.81640625, "max": 44473.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29950.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29950.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3868563771247864, "min": -0.1033395379781723, "max": 0.42454543709754944, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.13008117675781, "min": -24.491470336914062, "max": 114.62726593017578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0831557884812355, "min": 0.0009340783581137657, "max": 0.25009074807167053, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.953128814697266, "min": 0.23351958394050598, "max": 59.271507263183594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750249766369557, "min": 0.0671007574727853, "max": 0.07282650712352783, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0125374649554335, "min": 0.5097855498646948, "max": 1.0247697595429295, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015239865873526366, "min": 0.00045879194092309254, "max": 0.015239865873526366, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2285979881028955, "min": 0.0064230871729232955, "max": 0.2285979881028955, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.457897514066668e-06, "min": 7.457897514066668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011186846271100002, "min": 0.00011186846271100002, "max": 0.0033747319750894, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248593333333332, "min": 0.10248593333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537289, "min": 1.3886848, "max": 2.4856458000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025834474000000006, "min": 0.00025834474000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038751711000000006, "min": 0.0038751711000000006, "max": 0.11250856894, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008950818330049515, "min": 0.008950818330049515, "max": 0.29988595843315125, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13426227867603302, "min": 0.12804540991783142, "max": 2.0992016792297363, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 459.4925373134328, "min": 421.5138888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30786.0, "min": 16877.0, "max": 33859.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3016298129709798, "min": -1.0000000521540642, "max": 1.340955530840253, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.20919746905565, "min": -31.00000161677599, "max": 93.64459789544344, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3016298129709798, "min": -1.0000000521540642, "max": 1.340955530840253, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.20919746905565, "min": -31.00000161677599, "max": 93.64459789544344, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0422392873946619, "min": 0.0422392873946619, "max": 6.3593316976638405, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8300322554423474, "min": 2.8180216365435626, "max": 108.10863886028528, "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": "1740581738", "python_version": "3.10.9 (main, Mar 1 2023, 18:23:06) [GCC 11.2.0]", "command_line_arguments": "/home/slyne/anaconda3/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740583652" }, "total": 1914.6130660899798, "count": 1, "self": 0.420606364030391, "children": { "run_training.setup": { "total": 0.04079612996429205, "count": 1, "self": 0.04079612996429205 }, "TrainerController.start_learning": { "total": 1914.1516635959852, "count": 1, "self": 1.4270944509771653, "children": { "TrainerController._reset_env": { "total": 3.1132423329981975, "count": 1, "self": 3.1132423329981975 }, "TrainerController.advance": { "total": 1909.5181768460316, "count": 63499, "self": 1.4568346769665368, "children": { "env_step": { "total": 1169.3320196355926, "count": 63499, "self": 928.7022511632531, "children": { "SubprocessEnvManager._take_step": { "total": 239.70393887994578, "count": 63499, "self": 4.1007917377282865, "children": { "TorchPolicy.evaluate": { "total": 235.6031471422175, "count": 62570, "self": 235.6031471422175 } } }, "workers": { "total": 0.9258295923937112, "count": 63499, "self": 0.0, "children": { "worker_root": { "total": 1911.4425967605202, "count": 63499, "is_parallel": true, "self": 1068.979061680846, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002041561994701624, "count": 1, "is_parallel": true, "self": 0.0010165388230234385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010250231716781855, "count": 8, "is_parallel": true, "self": 0.0010250231716781855 } } }, "UnityEnvironment.step": { "total": 0.02868550398852676, "count": 1, "is_parallel": true, "self": 0.00024801905965432525, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023105001309886575, "count": 1, "is_parallel": true, "self": 0.00023105001309886575 }, "communicator.exchange": { "total": 0.027508394967298955, "count": 1, "is_parallel": true, "self": 0.027508394967298955 }, "steps_from_proto": { "total": 0.0006980399484746158, "count": 1, "is_parallel": true, "self": 0.00017568405019119382, "children": { "_process_rank_one_or_two_observation": { "total": 0.000522355898283422, "count": 8, "is_parallel": true, "self": 0.000522355898283422 } } } } } } }, "UnityEnvironment.step": { "total": 842.4635350796743, "count": 63498, "is_parallel": true, "self": 15.206904283957556, "children": { "UnityEnvironment._generate_step_input": { "total": 10.61818414798472, "count": 63498, "is_parallel": true, "self": 10.61818414798472 }, "communicator.exchange": { "total": 775.6549518626416, "count": 63498, "is_parallel": true, "self": 775.6549518626416 }, "steps_from_proto": { "total": 40.98349478509044, "count": 63498, "is_parallel": true, "self": 10.623980283271521, "children": { "_process_rank_one_or_two_observation": { "total": 30.35951450181892, "count": 507984, "is_parallel": true, "self": 30.35951450181892 } } } } } } } } } } }, "trainer_advance": { "total": 738.7293225334724, "count": 63499, "self": 2.5047118220827542, "children": { "process_trajectory": { "total": 121.70953914668644, "count": 63499, "self": 121.48223488969961, "children": { "RLTrainer._checkpoint": { "total": 0.22730425698682666, "count": 2, "self": 0.22730425698682666 } } }, "_update_policy": { "total": 614.5150715647032, "count": 449, "self": 260.11242785846116, "children": { "TorchPPOOptimizer.update": { "total": 354.4026437062421, "count": 22758, "self": 354.4026437062421 } } } } } } }, "trainer_threads": { "total": 6.039626896381378e-07, "count": 1, "self": 6.039626896381378e-07 }, "TrainerController._save_models": { "total": 0.09314936201553792, "count": 1, "self": 0.0008425250416621566, "children": { "RLTrainer._checkpoint": { "total": 0.09230683697387576, "count": 1, "self": 0.09230683697387576 } } } } } } }