{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41994068026542664, "min": 0.41994068026542664, "max": 1.551714539527893, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12497.4345703125, "min": 12497.4345703125, "max": 47072.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.902003824710846, "min": -0.13583017885684967, "max": 0.902003824710846, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 255.26708984375, "min": -32.73507308959961, "max": 255.26708984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017675092443823814, "min": 0.01516564842313528, "max": 0.21135880053043365, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.00205135345459, "min": 4.049228191375732, "max": 50.937469482421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06823321763243127, "min": 0.06724950507674034, "max": 0.07581049061181679, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4776325234270189, "min": 0.281222996790376, "max": 0.5898784818564309, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015233842444805693, "min": 0.0001892465855652302, "max": 0.015233842444805693, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10663689711363986, "min": 0.0011354795133913813, "max": 0.10663689711363986, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5817125935257134e-05, "min": 1.5817125935257134e-05, "max": 0.0005908992015167998, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011071988154679995, "min": 0.00011071988154679995, "max": 0.0036382206936299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10263617142857144, "min": 0.10263617142857144, "max": 0.19848319999999997, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7184532000000001, "min": 0.7184532000000001, "max": 1.3958485, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00027335352571428563, "min": 0.00027335352571428563, "max": 0.009848471680000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0019134746799999995, "min": 0.0019134746799999995, "max": 0.06064637299, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006166991777718067, "min": 0.006166991777718067, "max": 0.2599059045314789, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.043168943375349045, "min": 0.043168943375349045, "max": 1.0396236181259155, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.9, "min": 320.72727272727275, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33090.0, "min": 15984.0, "max": 33090.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5890819773077964, "min": -1.0000000521540642, "max": 1.6110658950426362, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.90819773077965, "min": -30.538001716136932, "max": 158.90819773077965, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5890819773077964, "min": -1.0000000521540642, "max": 1.6110658950426362, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.90819773077965, "min": -30.538001716136932, "max": 158.90819773077965, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021870249616877117, "min": 0.021870249616877117, "max": 7.622059701476246, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1870249616877118, "min": 1.9785366261785384, "max": 121.95295522361994, "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": "1710753241", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=PyramidsTraining --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710755840" }, "total": 2599.790075875, "count": 1, "self": 0.8725405100012722, "children": { "run_training.setup": { "total": 0.05263306199958606, "count": 1, "self": 0.05263306199958606 }, "TrainerController.start_learning": { "total": 2598.8649023029993, "count": 1, "self": 1.5426000491042942, "children": { "TrainerController._reset_env": { "total": 2.123081154000829, "count": 1, "self": 2.123081154000829 }, "TrainerController.advance": { "total": 2595.0717567448937, "count": 63930, "self": 1.5202277659027459, "children": { "env_step": { "total": 1604.6939653011868, "count": 63930, "self": 1464.4834829431948, "children": { "SubprocessEnvManager._take_step": { "total": 139.27501445393136, "count": 63930, "self": 4.9969301359051315, "children": { "TorchPolicy.evaluate": { "total": 134.27808431802623, "count": 62549, "self": 134.27808431802623 } } }, "workers": { "total": 0.9354679040607152, "count": 63930, "self": 0.0, "children": { "worker_root": { "total": 2593.2434086469657, "count": 63930, "is_parallel": true, "self": 1258.1205575938802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022402710001188098, "count": 1, "is_parallel": true, "self": 0.0006676819994027028, "children": { "_process_rank_one_or_two_observation": { "total": 0.001572589000716107, "count": 8, "is_parallel": true, "self": 0.001572589000716107 } } }, "UnityEnvironment.step": { "total": 0.059136515999853145, "count": 1, "is_parallel": true, "self": 0.0007317520012293244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005336119993444299, "count": 1, "is_parallel": true, "self": 0.0005336119993444299 }, "communicator.exchange": { "total": 0.05592021200027375, "count": 1, "is_parallel": true, "self": 0.05592021200027375 }, "steps_from_proto": { "total": 0.0019509399990056409, "count": 1, "is_parallel": true, "self": 0.0004174999958195258, "children": { "_process_rank_one_or_two_observation": { "total": 0.001533440003186115, "count": 8, "is_parallel": true, "self": 0.001533440003186115 } } } } } } }, "UnityEnvironment.step": { "total": 1335.1228510530855, "count": 63929, "is_parallel": true, "self": 36.146047124886536, "children": { "UnityEnvironment._generate_step_input": { "total": 25.554368457811506, "count": 63929, "is_parallel": true, "self": 25.554368457811506 }, "communicator.exchange": { "total": 1165.8202195499944, "count": 63929, "is_parallel": true, "self": 1165.8202195499944 }, "steps_from_proto": { "total": 107.60221592039306, "count": 63929, "is_parallel": true, "self": 22.09969272111448, "children": { "_process_rank_one_or_two_observation": { "total": 85.50252319927858, "count": 511432, "is_parallel": true, "self": 85.50252319927858 } } } } } } } } } } }, "trainer_advance": { "total": 988.8575636778041, "count": 63930, "self": 2.8985726268674625, "children": { "process_trajectory": { "total": 133.4653514649217, "count": 63930, "self": 133.2155993949218, "children": { "RLTrainer._checkpoint": { "total": 0.24975206999988586, "count": 2, "self": 0.24975206999988586 } } }, "_update_policy": { "total": 852.493639586015, "count": 233, "self": 498.28564872619427, "children": { "TorchPPOOptimizer.update": { "total": 354.2079908598207, "count": 38495, "self": 354.2079908598207 } } } } } } }, "trainer_threads": { "total": 1.2920008884975687e-06, "count": 1, "self": 1.2920008884975687e-06 }, "TrainerController._save_models": { "total": 0.12746306299959542, "count": 1, "self": 0.0026267180001013912, "children": { "RLTrainer._checkpoint": { "total": 0.12483634499949403, "count": 1, "self": 0.12483634499949403 } } } } } } }