{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3927719295024872, "min": 0.3345213234424591, "max": 1.5908561944961548, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11751.736328125, "min": 9982.1162109375, "max": 48260.21484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06096706911921501, "min": -0.13392141461372375, "max": -0.058662671595811844, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.693063735961914, "min": -31.739376068115234, "max": -14.267111778259277, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030788179486989975, "min": 0.026850635185837746, "max": 0.4137192666530609, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.419951438903809, "min": 6.47100305557251, "max": 99.70634460449219, "count": 33 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.5742224454879761, "min": 0.5742224454879761, "max": 3.045016050338745, "count": 33 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 138.38760375976562, "min": 136.74951171875, "max": 733.848876953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.02909161233032743, "min": 0.028808268814140725, "max": 0.04354854062143149, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.14545806165163716, "min": 0.136160298956163, "max": 0.21774270310715746, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001329722151470681, "min": 0.0004763982726162243, "max": 0.040207329172655154, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.006648610757353405, "min": 0.0023819913630811216, "max": 0.16082931669062062, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.599277466940001e-06, "min": 7.599277466940001e-06, "max": 0.00029544960151680006, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.7996387334700006e-05, "min": 3.7996387334700006e-05, "max": 0.0016110864629711996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253306, "min": 0.10253306, "max": 0.19848320000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5126653, "min": 0.5126653, "max": 1.1370288000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 3.507729400000001e-05, "min": 3.507729400000001e-05, "max": 0.0009849836800000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00017538647000000002, "min": 0.00017538647000000002, "max": 0.00537658512, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.026291707530617714, "min": 0.026291707530617714, "max": 0.5129854679107666, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13145853579044342, "min": 0.13145853579044342, "max": 2.3161582946777344, "count": 33 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.054038520380854604, "min": 0.054038520380854604, "max": 0.5813339463519779, "count": 33 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 0.270192601904273, "min": 0.270192601904273, "max": 2.3253357854079115, "count": 33 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.11195765189826487, "min": 0.10988195906910632, "max": 1.0550547594373876, "count": 33 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 0.5597882594913244, "min": 0.5597882594913244, "max": 4.22021903774955, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 964.8064516129032, "min": 804.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29909.0, "min": 15984.0, "max": 33199.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7718323077405652, "min": -1.0000000521540642, "max": -0.09919416334699183, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.926801539957523, "min": -31.996801659464836, "max": -3.372601553797722, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7718323077405652, "min": -1.0000000521540642, "max": -0.09919416334699183, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.926801539957523, "min": -31.996801659464836, "max": -3.372601553797722, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2740312070555745, "min": 0.25448191026225686, "max": 6.806104302406311, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 8.494967418722808, "min": 7.634457307867706, "max": 175.9811226129532, "count": 33 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 5.350721614014718, "min": 5.3234859297672905, "max": 42.04442534727209, "count": 33 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 165.87237003445625, "min": 159.70457789301872, "max": 1429.510461807251, "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": "1676560841", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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 2 --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": "1676563000" }, "total": 2159.1076753690004, "count": 1, "self": 0.47553678899930674, "children": { "run_training.setup": { "total": 0.12349426800028596, "count": 1, "self": 0.12349426800028596 }, "TrainerController.start_learning": { "total": 2158.508644312001, "count": 1, "self": 1.3994665169266227, "children": { "TrainerController._reset_env": { "total": 7.210593030000382, "count": 1, "self": 7.210593030000382 }, "TrainerController.advance": { "total": 2149.809942970074, "count": 62930, "self": 1.4435820270491604, "children": { "env_step": { "total": 1445.1240899059467, "count": 62930, "self": 1329.0530054199216, "children": { "SubprocessEnvManager._take_step": { "total": 115.2503089261254, "count": 62930, "self": 4.758791506123998, "children": { "TorchPolicy.evaluate": { "total": 110.4915174200014, "count": 62561, "self": 36.89906582790354, "children": { "TorchPolicy.sample_actions": { "total": 73.59245159209786, "count": 62561, "self": 73.59245159209786 } } } } }, "workers": { "total": 0.82077555989963, "count": 62930, "self": 0.0, "children": { "worker_root": { "total": 2153.7299986752214, "count": 62930, "is_parallel": true, "self": 939.2318687921997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020292749995860504, "count": 1, "is_parallel": true, "self": 0.0007508389981012442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012784360014848062, "count": 8, "is_parallel": true, "self": 0.0012784360014848062 } } }, "UnityEnvironment.step": { "total": 0.04860341199946561, "count": 1, "is_parallel": true, "self": 0.0007584909990328015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005181970000194269, "count": 1, "is_parallel": true, "self": 0.0005181970000194269 }, "communicator.exchange": { "total": 0.04565544300021429, "count": 1, "is_parallel": true, "self": 0.04565544300021429 }, "steps_from_proto": { "total": 0.0016712810001990874, "count": 1, "is_parallel": true, "self": 0.00040697900021768874, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012643019999813987, "count": 8, "is_parallel": true, "self": 0.0012643019999813987 } } } } } } }, "UnityEnvironment.step": { "total": 1214.4981298830216, "count": 62929, "is_parallel": true, "self": 31.409194018135167, "children": { "UnityEnvironment._generate_step_input": { "total": 23.935441597883255, "count": 62929, "is_parallel": true, "self": 23.935441597883255 }, "communicator.exchange": { "total": 1055.1223136239896, "count": 62929, "is_parallel": true, "self": 1055.1223136239896 }, "steps_from_proto": { "total": 104.03118064301361, "count": 62929, "is_parallel": true, "self": 23.448206617877076, "children": { "_process_rank_one_or_two_observation": { "total": 80.58297402513654, "count": 503432, "is_parallel": true, "self": 80.58297402513654 } } } } } } } } } } }, "trainer_advance": { "total": 703.2422710370784, "count": 62930, "self": 2.2271853410020412, "children": { "process_trajectory": { "total": 187.03582389406893, "count": 62930, "self": 186.76798699206847, "children": { "RLTrainer._checkpoint": { "total": 0.26783690200045385, "count": 2, "self": 0.26783690200045385 } } }, "_update_policy": { "total": 513.9792618020074, "count": 180, "self": 241.91819204698822, "children": { "TorchPPOOptimizer.update": { "total": 272.06106975501916, "count": 5679, "self": 272.06106975501916 } } } } } } }, "trainer_threads": { "total": 9.369996405439451e-07, "count": 1, "self": 9.369996405439451e-07 }, "TrainerController._save_models": { "total": 0.08864085799996246, "count": 1, "self": 0.001518477999525203, "children": { "RLTrainer._checkpoint": { "total": 0.08712238000043726, "count": 1, "self": 0.08712238000043726 } } } } } } }