{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40420493483543396, "min": 0.39900603890419006, "max": 0.4830927848815918, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 12132.615234375, "min": 12021.25390625, "max": 14948.8232421875, "count": 7 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.73417721518985, "min": 364.92537313432837, "max": 548.280701754386, "count": 7 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31026.0, "min": 24450.0, "max": 31714.0, "count": 7 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 809998.0, "max": 989880.0, "count": 7 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 809998.0, "max": 989880.0, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44328415393829346, "min": 0.30201780796051025, "max": 0.44328415393829346, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.01657104492188, "min": 77.61857604980469, "max": 121.01657104492188, "count": 7 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005800439510494471, "min": -0.011447438970208168, "max": 0.02458082139492035, "count": 7 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.5835199356079102, "min": -3.1365983486175537, "max": 6.464756011962891, "count": 7 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5313063112995293, "min": 1.0754447967327874, "max": 1.5454865443839956, "count": 7 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.97319859266281, "min": 62.37579821050167, "max": 120.97319859266281, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5313063112995293, "min": 1.0754447967327874, "max": 1.5454865443839956, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.97319859266281, "min": 62.37579821050167, "max": 120.97319859266281, "count": 7 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043718275764391204, "min": 0.043718275764391204, "max": 0.06089715182867527, "count": 7 }, "Pyramids.Policy.RndReward.sum": { "value": 3.453743785386905, "min": 3.2254289740812965, "max": 3.7782387666520663, "count": 7 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06900275927196785, "min": 0.06511649959083157, "max": 0.07208056387311193, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0350413890795178, "min": 0.9116309942716421, "max": 1.0350413890795178, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015598284871126465, "min": 0.012546473937358573, "max": 0.015826248938507332, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23397427306689697, "min": 0.17565063512302004, "max": 0.23397427306689697, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.495737501453336e-06, "min": 7.495737501453336e-06, "max": 6.120948673972143e-05, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011243606252180004, "min": 0.00011243606252180004, "max": 0.0008569328143561002, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249854666666666, "min": 0.10249854666666666, "max": 0.12040313571428572, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374782, "min": 1.4780311, "max": 1.6856439, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025960481200000015, "min": 0.00025960481200000015, "max": 0.002048273257857144, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038940721800000025, "min": 0.0038940721800000025, "max": 0.02867582561000001, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01057474222034216, "min": 0.01057474222034216, "max": 0.01273829024285078, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15862113237380981, "min": 0.1546945869922638, "max": 0.17833606898784637, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739039481", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739040012" }, "total": 531.513850113, "count": 1, "self": 0.48228738699936, "children": { "run_training.setup": { "total": 0.055961961000321025, "count": 1, "self": 0.055961961000321025 }, "TrainerController.start_learning": { "total": 530.9756007650003, "count": 1, "self": 0.3862626329973864, "children": { "TrainerController._reset_env": { "total": 3.985030438999729, "count": 1, "self": 3.985030438999729 }, "TrainerController.advance": { "total": 526.5141532140037, "count": 14201, "self": 0.37557371399998374, "children": { "env_step": { "total": 372.5937489519779, "count": 14201, "self": 334.7986020489625, "children": { "SubprocessEnvManager._take_step": { "total": 37.57660660101101, "count": 14201, "self": 1.1129458040259124, "children": { "TorchPolicy.evaluate": { "total": 36.463660796985096, "count": 13789, "self": 36.463660796985096 } } }, "workers": { "total": 0.218540302004385, "count": 14201, "self": 0.0, "children": { "worker_root": { "total": 529.4517286559958, "count": 14201, "is_parallel": true, "self": 222.94533792194898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024672900003679388, "count": 1, "is_parallel": true, "self": 0.0007143660004658159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017529239999021229, "count": 8, "is_parallel": true, "self": 0.0017529239999021229 } } }, "UnityEnvironment.step": { "total": 0.049989174000074854, "count": 1, "is_parallel": true, "self": 0.0005364729995562811, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046456600011879345, "count": 1, "is_parallel": true, "self": 0.00046456600011879345 }, "communicator.exchange": { "total": 0.047418617000403174, "count": 1, "is_parallel": true, "self": 0.047418617000403174 }, "steps_from_proto": { "total": 0.0015695179999966058, "count": 1, "is_parallel": true, "self": 0.00033694400099193444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012325739990046714, "count": 8, "is_parallel": true, "self": 0.0012325739990046714 } } } } } } }, "UnityEnvironment.step": { "total": 306.5063907340468, "count": 14200, "is_parallel": true, "self": 7.282236440089491, "children": { "UnityEnvironment._generate_step_input": { "total": 5.133130172991969, "count": 14200, "is_parallel": true, "self": 5.133130172991969 }, "communicator.exchange": { "total": 272.3355497059879, "count": 14200, "is_parallel": true, "self": 272.3355497059879 }, "steps_from_proto": { "total": 21.75547441497747, "count": 14200, "is_parallel": true, "self": 4.6582729780766385, "children": { "_process_rank_one_or_two_observation": { "total": 17.097201436900832, "count": 113600, "is_parallel": true, "self": 17.097201436900832 } } } } } } } } } } }, "trainer_advance": { "total": 153.54483054802586, "count": 14201, "self": 0.781521444045211, "children": { "process_trajectory": { "total": 29.707514030981656, "count": 14201, "self": 29.543071906981822, "children": { "RLTrainer._checkpoint": { "total": 0.1644421239998337, "count": 1, "self": 0.1644421239998337 } } }, "_update_policy": { "total": 123.05579507299899, "count": 103, "self": 67.80614840899989, "children": { "TorchPPOOptimizer.update": { "total": 55.2496466639991, "count": 4956, "self": 55.2496466639991 } } } } } } }, "trainer_threads": { "total": 1.1069996617152356e-06, "count": 1, "self": 1.1069996617152356e-06 }, "TrainerController._save_models": { "total": 0.09015337199980422, "count": 1, "self": 0.0020727119999719434, "children": { "RLTrainer._checkpoint": { "total": 0.08808065999983228, "count": 1, "self": 0.08808065999983228 } } } } } } }