{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17879296839237213, "min": 0.17879296839237213, "max": 0.1970229297876358, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 5441.02783203125, "min": 1423.072509765625, "max": 5986.1630859375, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 216.4857142857143, "min": 167.3030303030303, "max": 242.1811023622047, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30308.0, "min": 5521.0, "max": 31114.0, "count": 10 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 2729936.0, "max": 2999965.0, "count": 10 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 2729936.0, "max": 2999965.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.823097288608551, "min": 0.778925895690918, "max": 0.8774658441543579, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 247.75228881835938, "min": 54.91301727294922, "max": 269.38201904296875, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015164838172495365, "min": 0.009346856735646725, "max": 0.024456864222884178, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.5646162033081055, "min": 1.302393913269043, "max": 7.5082573890686035, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7683064606335523, "min": 1.733974230108839, "max": 1.8385312431491911, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.79459802806377, "min": 58.83299978077412, "max": 267.4769981354475, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7683064606335523, "min": 1.733974230108839, "max": 1.8385312431491911, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.79459802806377, "min": 58.83299978077412, "max": 267.4769981354475, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013927758147264999, "min": 0.010947162330012361, "max": 0.015619884484459456, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9359583824698348, "min": 0.35030919456039555, "max": 2.0279621132176544, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07080976019795406, "min": 0.06440852031422159, "max": 0.07367122080841483, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9913366427713567, "min": 0.21377060843709234, "max": 1.034536091046974, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015784795296408437, "min": 0.013109744551174609, "max": 0.015784795296408437, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2209871341497181, "min": 0.0398591702299503, "max": 0.2209871341497181, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4901852175904787e-06, "min": 1.4901852175904787e-06, "max": 2.728682423775556e-05, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.08625930462667e-05, "min": 2.08625930462667e-05, "max": 0.00035706928097733337, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049669523809525, "min": 0.10049669523809525, "max": 0.10909557777777779, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069537333333335, "min": 0.32728673333333336, "max": 1.5976366000000002, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 5.961985428571438e-05, "min": 5.961985428571438e-05, "max": 0.0009186482200000001, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008346779600000013, "min": 0.0008346779600000013, "max": 0.012030364400000004, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006179290357977152, "min": 0.0059756748378276825, "max": 0.006409128662198782, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0865100622177124, "min": 0.01922738552093506, "max": 0.09408923983573914, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676493886", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/home/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/venv/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "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": "1.23.5", "end_time_seconds": "1676494257" }, "total": 370.97769310697913, "count": 1, "self": 0.26875200995709747, "children": { "run_training.setup": { "total": 0.011147813056595623, "count": 1, "self": 0.011147813056595623 }, "TrainerController.start_learning": { "total": 370.69779328396544, "count": 1, "self": 0.26226116030011326, "children": { "TrainerController._reset_env": { "total": 2.508407872985117, "count": 1, "self": 2.508407872985117 }, "TrainerController.advance": { "total": 367.8717266586609, "count": 18385, "self": 0.24454630725085735, "children": { "env_step": { "total": 243.6402637831634, "count": 18385, "self": 223.39526666142046, "children": { "SubprocessEnvManager._take_step": { "total": 20.07255873340182, "count": 18385, "self": 0.6583400904200971, "children": { "TorchPolicy.evaluate": { "total": 19.414218642981723, "count": 17387, "self": 6.798493409063667, "children": { "TorchPolicy.sample_actions": { "total": 12.615725233918056, "count": 17387, "self": 12.615725233918056 } } } } }, "workers": { "total": 0.17243838834110647, "count": 18385, "self": 0.0, "children": { "worker_root": { "total": 370.1284821955487, "count": 18385, "is_parallel": true, "self": 165.1358080446953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001776541001163423, "count": 1, "is_parallel": true, "self": 0.0005160352448001504, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012605057563632727, "count": 8, "is_parallel": true, "self": 0.0012605057563632727 } } }, "UnityEnvironment.step": { "total": 0.03065299103036523, "count": 1, "is_parallel": true, "self": 0.00040160201024264097, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003713839687407017, "count": 1, "is_parallel": true, "self": 0.0003713839687407017 }, "communicator.exchange": { "total": 0.028839179081842303, "count": 1, "is_parallel": true, "self": 0.028839179081842303 }, "steps_from_proto": { "total": 0.0010408259695395827, "count": 1, "is_parallel": true, "self": 0.0002575409598648548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007832850096747279, "count": 8, "is_parallel": true, "self": 0.0007832850096747279 } } } } } } }, "UnityEnvironment.step": { "total": 204.99267415085342, "count": 18384, "is_parallel": true, "self": 6.976059003151022, "children": { "UnityEnvironment._generate_step_input": { "total": 4.559130738256499, "count": 18384, "is_parallel": true, "self": 4.559130738256499 }, "communicator.exchange": { "total": 176.83691698755138, "count": 18384, "is_parallel": true, "self": 176.83691698755138 }, "steps_from_proto": { "total": 16.62056742189452, "count": 18384, "is_parallel": true, "self": 3.8805037991842255, "children": { "_process_rank_one_or_two_observation": { "total": 12.740063622710295, "count": 147072, "is_parallel": true, "self": 12.740063622710295 } } } } } } } } } } }, "trainer_advance": { "total": 123.98691656824667, "count": 18385, "self": 0.48568377597257495, "children": { "process_trajectory": { "total": 27.415473963483237, "count": 18385, "self": 27.350462592439726, "children": { "RLTrainer._checkpoint": { "total": 0.06501137104351074, "count": 1, "self": 0.06501137104351074 } } }, "_update_policy": { "total": 96.08575882879086, "count": 131, "self": 30.86648914287798, "children": { "TorchPPOOptimizer.update": { "total": 65.21926968591288, "count": 6303, "self": 65.21926968591288 } } } } } } }, "trainer_threads": { "total": 5.910405889153481e-07, "count": 1, "self": 5.910405889153481e-07 }, "TrainerController._save_models": { "total": 0.05539700097870082, "count": 1, "self": 0.0010045889066532254, "children": { "RLTrainer._checkpoint": { "total": 0.05439241207204759, "count": 1, "self": 0.05439241207204759 } } } } } } }