{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13602660596370697, "min": 0.13583901524543762, "max": 1.4202266931533813, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4061.210205078125, "min": 4061.210205078125, "max": 43083.99609375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999995.0, "min": 29952.0, "max": 2999995.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999995.0, "min": 29952.0, "max": 2999995.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8167455792427063, "min": -0.11929839849472046, "max": 0.8687863945960999, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.2906494140625, "min": -28.750913619995117, "max": 264.9798583984375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007924986071884632, "min": -0.007557711098343134, "max": 0.2994096875190735, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.409195899963379, "min": -2.282428741455078, "max": 70.96009826660156, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07180639234994647, "min": 0.06467965387578478, "max": 0.07354237724142702, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0052894928992506, "min": 0.5069143521187502, "max": 1.0881473115184823, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014513328863605884, "min": 0.00043650309756104115, "max": 0.016150270022557207, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20318660409048236, "min": 0.006111043365854576, "max": 0.23994946052941182, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5093923540452372e-06, "min": 1.5093923540452372e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.113149295663332e-05, "min": 2.113149295663332e-05, "max": 0.003886035004655033, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050309761904763, "min": 0.10050309761904763, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070433666666669, "min": 1.3962282666666668, "max": 2.737508166666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0259452142857104e-05, "min": 6.0259452142857104e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008436323299999994, "min": 0.0008436323299999994, "max": 0.12954496217, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005743837915360928, "min": 0.005099236499518156, "max": 0.4340144693851471, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08041372895240784, "min": 0.07138931006193161, "max": 3.0381011962890625, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 230.6159420289855, "min": 205.32, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31825.0, "min": 15984.0, "max": 32805.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7548883915811344, "min": -1.0000000521540642, "max": 1.7946799803773563, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 242.17459803819656, "min": -30.61080165207386, "max": 269.20199705660343, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7548883915811344, "min": -1.0000000521540642, "max": 1.7946799803773563, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 242.17459803819656, "min": -30.61080165207386, "max": 269.20199705660343, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01364358134626367, "min": 0.012833096896235172, "max": 8.598184479400516, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8828142257843865, "min": 1.63409340058206, "max": 137.57095167040825, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700315365", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700326363" }, "total": 10998.11913512, "count": 1, "self": 0.5867473859998427, "children": { "run_training.setup": { "total": 0.05915674199991372, "count": 1, "self": 0.05915674199991372 }, "TrainerController.start_learning": { "total": 10997.473230992, "count": 1, "self": 6.927519659227983, "children": { "TrainerController._reset_env": { "total": 2.8049988800000847, "count": 1, "self": 2.8049988800000847 }, "TrainerController.advance": { "total": 10987.656239836773, "count": 194594, "self": 7.548685500563806, "children": { "env_step": { "total": 7621.457590666028, "count": 194594, "self": 7132.142724149411, "children": { "SubprocessEnvManager._take_step": { "total": 484.97251919759856, "count": 194594, "self": 21.393180404491886, "children": { "TorchPolicy.evaluate": { "total": 463.5793387931067, "count": 187563, "self": 463.5793387931067 } } }, "workers": { "total": 4.342347319019154, "count": 194594, "self": 0.0, "children": { "worker_root": { "total": 10977.246726332762, "count": 194594, "is_parallel": true, "self": 4385.43413587985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002993773000071087, "count": 1, "is_parallel": true, "self": 0.00105503299960219, "children": { "_process_rank_one_or_two_observation": { "total": 0.001938740000468897, "count": 8, "is_parallel": true, "self": 0.001938740000468897 } } }, "UnityEnvironment.step": { "total": 0.12259535599991978, "count": 1, "is_parallel": true, "self": 0.0006812059998537734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005094510001981689, "count": 1, "is_parallel": true, "self": 0.0005094510001981689 }, "communicator.exchange": { "total": 0.11934475499992914, "count": 1, "is_parallel": true, "self": 0.11934475499992914 }, "steps_from_proto": { "total": 0.002059943999938696, "count": 1, "is_parallel": true, "self": 0.0003895449999617995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016703989999768964, "count": 8, "is_parallel": true, "self": 0.0016703989999768964 } } } } } } }, "UnityEnvironment.step": { "total": 6591.8125904529115, "count": 194593, "is_parallel": true, "self": 139.77660959328114, "children": { "UnityEnvironment._generate_step_input": { "total": 84.73762966455911, "count": 194593, "is_parallel": true, "self": 84.73762966455911 }, "communicator.exchange": { "total": 5975.337384494072, "count": 194593, "is_parallel": true, "self": 5975.337384494072 }, "steps_from_proto": { "total": 391.96096670099973, "count": 194593, "is_parallel": true, "self": 82.95895192020203, "children": { "_process_rank_one_or_two_observation": { "total": 309.0020147807977, "count": 1556744, "is_parallel": true, "self": 309.0020147807977 } } } } } } } } } } }, "trainer_advance": { "total": 3358.649963670181, "count": 194594, "self": 14.801361933035878, "children": { "process_trajectory": { "total": 517.2268389411629, "count": 194594, "self": 516.6760005451624, "children": { "RLTrainer._checkpoint": { "total": 0.5508383960004721, "count": 6, "self": 0.5508383960004721 } } }, "_update_policy": { "total": 2826.6217627959822, "count": 1399, "self": 1153.6336641089028, "children": { "TorchPPOOptimizer.update": { "total": 1672.9880986870794, "count": 68415, "self": 1672.9880986870794 } } } } } } }, "trainer_threads": { "total": 1.4739998732693493e-06, "count": 1, "self": 1.4739998732693493e-06 }, "TrainerController._save_models": { "total": 0.08447114199952921, "count": 1, "self": 0.0025762770001165336, "children": { "RLTrainer._checkpoint": { "total": 0.08189486499941268, "count": 1, "self": 0.08189486499941268 } } } } } } }