{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5017765164375305, "min": 0.47131940722465515, "max": 1.4657517671585083, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14989.068359375, "min": 13973.677734375, "max": 44465.046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29928.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29928.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49206286668777466, "min": -0.09133850783109665, "max": 0.497018039226532, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.3649139404297, "min": -22.01258087158203, "max": 135.18890380859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022685877978801727, "min": -0.00409579137340188, "max": 0.4311545193195343, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.102501392364502, "min": -1.0812889337539673, "max": 102.18362426757812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06991457683058698, "min": 0.06700011042574058, "max": 0.07419040419203468, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9788040756282177, "min": 0.4956733811341946, "max": 1.0830063278165956, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014557455554757796, "min": 0.0006597017376413627, "max": 0.016533232685233136, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20380437776660915, "min": 0.008576122589337714, "max": 0.23146525759326392, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.741340276728568e-06, "min": 7.741340276728568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010837876387419996, "min": 0.00010837876387419996, "max": 0.0035084720305094, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025804142857143, "min": 0.1025804142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361258000000001, "min": 1.3691136000000002, "max": 2.5694906, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026778338714285706, "min": 0.00026778338714285706, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003748967419999999, "min": 0.003748967419999999, "max": 0.11697211094000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011144165880978107, "min": 0.011144165880978107, "max": 0.5155397057533264, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15601831674575806, "min": 0.15601831674575806, "max": 3.6087779998779297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 445.2307692307692, "min": 338.2168674698795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28940.0, "min": 16855.0, "max": 32647.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4008738233492926, "min": -0.9999936006722911, "max": 1.5894650408481976, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.05679851770401, "min": -30.999801620841026, "max": 131.9255983904004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4008738233492926, "min": -0.9999936006722911, "max": 1.5894650408481976, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.05679851770401, "min": -30.999801620841026, "max": 131.9255983904004, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05047016120515764, "min": 0.042221275512381536, "max": 10.658538680742769, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2805604783352464, "min": 3.2805604783352464, "max": 181.19515757262707, "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": "1793435597", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/mlenv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1793437674" }, "total": 2077.186999893, "count": 1, "self": 0.4806621830007316, "children": { "run_training.setup": { "total": 0.014658117999942988, "count": 1, "self": 0.014658117999942988 }, "TrainerController.start_learning": { "total": 2076.6916795919997, "count": 1, "self": 1.3086670389916435, "children": { "TrainerController._reset_env": { "total": 1.6168985790000079, "count": 1, "self": 1.6168985790000079 }, "TrainerController.advance": { "total": 2073.7072725730077, "count": 63687, "self": 1.342653144941778, "children": { "env_step": { "total": 1365.073682236995, "count": 63687, "self": 1271.5646568339723, "children": { "SubprocessEnvManager._take_step": { "total": 92.74649039500082, "count": 63687, "self": 4.631748111992465, "children": { "TorchPolicy.evaluate": { "total": 88.11474228300835, "count": 62582, "self": 88.11474228300835 } } }, "workers": { "total": 0.7625350080218141, "count": 63687, "self": 0.0, "children": { "worker_root": { "total": 2073.787165913946, "count": 63687, "is_parallel": true, "self": 907.1839848279471, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019407550000778429, "count": 1, "is_parallel": true, "self": 0.0006527440000354545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012880110000423883, "count": 8, "is_parallel": true, "self": 0.0012880110000423883 } } }, "UnityEnvironment.step": { "total": 0.04697052400001667, "count": 1, "is_parallel": true, "self": 0.000541257000350015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041279099991697876, "count": 1, "is_parallel": true, "self": 0.00041279099991697876 }, "communicator.exchange": { "total": 0.04409504599993852, "count": 1, "is_parallel": true, "self": 0.04409504599993852 }, "steps_from_proto": { "total": 0.0019214299998111528, "count": 1, "is_parallel": true, "self": 0.0006607360000998597, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012606939997112931, "count": 8, "is_parallel": true, "self": 0.0012606939997112931 } } } } } } }, "UnityEnvironment.step": { "total": 1166.6031810859988, "count": 63686, "is_parallel": true, "self": 31.920421560057775, "children": { "UnityEnvironment._generate_step_input": { "total": 21.706745846011472, "count": 63686, "is_parallel": true, "self": 21.706745846011472 }, "communicator.exchange": { "total": 1013.1939292479333, "count": 63686, "is_parallel": true, "self": 1013.1939292479333 }, "steps_from_proto": { "total": 99.78208443199628, "count": 63686, "is_parallel": true, "self": 21.385580828911998, "children": { "_process_rank_one_or_two_observation": { "total": 78.39650360308428, "count": 509488, "is_parallel": true, "self": 78.39650360308428 } } } } } } } } } } }, "trainer_advance": { "total": 707.290937191071, "count": 63687, "self": 2.4773947040325766, "children": { "process_trajectory": { "total": 114.88425430703933, "count": 63687, "self": 114.74497641203948, "children": { "RLTrainer._checkpoint": { "total": 0.1392778949998501, "count": 2, "self": 0.1392778949998501 } } }, "_update_policy": { "total": 589.929288179999, "count": 448, "self": 275.5192716939798, "children": { "TorchPPOOptimizer.update": { "total": 314.41001648601923, "count": 22839, "self": 314.41001648601923 } } } } } } }, "trainer_threads": { "total": 9.020000106829684e-07, "count": 1, "self": 9.020000106829684e-07 }, "TrainerController._save_models": { "total": 0.05884049900032551, "count": 1, "self": 0.001087604000531428, "children": { "RLTrainer._checkpoint": { "total": 0.05775289499979408, "count": 1, "self": 0.05775289499979408 } } } } } } }