{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5572212338447571, "min": 0.5313510298728943, "max": 1.3568257093429565, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16877.1171875, "min": 15864.0166015625, "max": 41160.6640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3921082019805908, "min": -0.11090000718832016, "max": 0.3921082019805908, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.12445831298828, "min": -26.72690200805664, "max": 103.12445831298828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024273036047816277, "min": 0.008581387810409069, "max": 0.6915910840034485, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.383808612823486, "min": 2.2569050788879395, "max": 163.90708923339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06722213421245198, "min": 0.06471642829031035, "max": 0.07238377535858202, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9411098789743277, "min": 0.49803677136540125, "max": 1.0728718937173778, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014455548680701874, "min": 0.0008888728146294917, "max": 0.02224176698267066, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20237768152982624, "min": 0.011555346590183391, "max": 0.22317395074545246, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.462554655371428e-06, "min": 7.462554655371428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001044757651752, "min": 0.0001044757651752, "max": 0.0035078384307205995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248748571428572, "min": 0.10248748571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348248000000001, "min": 1.3886848, "max": 2.5692794, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584998228571429, "min": 0.0002584998228571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003618997520000001, "min": 0.003618997520000001, "max": 0.11695101205999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017986873164772987, "min": 0.017986873164772987, "max": 0.8519040942192078, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2518162131309509, "min": 0.2518162131309509, "max": 5.963328838348389, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 477.0, "min": 448.02702702702703, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30528.0, "min": 15984.0, "max": 33189.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.486563057395128, "min": -1.0000000521540642, "max": 1.486563057395128, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 96.62659873068333, "min": -28.55000176280737, "max": 96.84079781919718, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.486563057395128, "min": -1.0000000521540642, "max": 1.486563057395128, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 96.62659873068333, "min": -28.55000176280737, "max": 96.84079781919718, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08933411526242988, "min": 0.08933411526242988, "max": 18.009875506162643, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.806717492057942, "min": 5.5923092816374265, "max": 288.1580080986023, "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": "1740954582", "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", "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": "1740956819" }, "total": 2236.9699484220005, "count": 1, "self": 0.48721256100088794, "children": { "run_training.setup": { "total": 0.02798575599990727, "count": 1, "self": 0.02798575599990727 }, "TrainerController.start_learning": { "total": 2236.4547501049997, "count": 1, "self": 1.5515237290469486, "children": { "TrainerController._reset_env": { "total": 3.0586536779997004, "count": 1, "self": 3.0586536779997004 }, "TrainerController.advance": { "total": 2231.7551513649537, "count": 63457, "self": 1.5982278158148802, "children": { "env_step": { "total": 1539.3480529101153, "count": 63457, "self": 1372.2075556991695, "children": { "SubprocessEnvManager._take_step": { "total": 166.24055143689748, "count": 63457, "self": 4.917933683906085, "children": { "TorchPolicy.evaluate": { "total": 161.3226177529914, "count": 62554, "self": 161.3226177529914 } } }, "workers": { "total": 0.8999457740483194, "count": 63457, "self": 0.0, "children": { "worker_root": { "total": 2230.8385327349297, "count": 63457, "is_parallel": true, "self": 979.6594968620016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026687009999477596, "count": 1, "is_parallel": true, "self": 0.0008144610001181718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018542399998295878, "count": 8, "is_parallel": true, "self": 0.0018542399998295878 } } }, "UnityEnvironment.step": { "total": 0.049150328999985504, "count": 1, "is_parallel": true, "self": 0.00061234799977683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045012000009592157, "count": 1, "is_parallel": true, "self": 0.00045012000009592157 }, "communicator.exchange": { "total": 0.046408709000388626, "count": 1, "is_parallel": true, "self": 0.046408709000388626 }, "steps_from_proto": { "total": 0.0016791519997241267, "count": 1, "is_parallel": true, "self": 0.0003545960003066284, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013245559994174982, "count": 8, "is_parallel": true, "self": 0.0013245559994174982 } } } } } } }, "UnityEnvironment.step": { "total": 1251.1790358729281, "count": 63456, "is_parallel": true, "self": 32.35498800687719, "children": { "UnityEnvironment._generate_step_input": { "total": 22.706238080006187, "count": 63456, "is_parallel": true, "self": 22.706238080006187 }, "communicator.exchange": { "total": 1099.37503629805, "count": 63456, "is_parallel": true, "self": 1099.37503629805 }, "steps_from_proto": { "total": 96.74277348799478, "count": 63456, "is_parallel": true, "self": 19.938583394918624, "children": { "_process_rank_one_or_two_observation": { "total": 76.80419009307616, "count": 507648, "is_parallel": true, "self": 76.80419009307616 } } } } } } } } } } }, "trainer_advance": { "total": 690.8088706390236, "count": 63457, "self": 3.051908108974203, "children": { "process_trajectory": { "total": 128.66972856905068, "count": 63457, "self": 128.36180330305024, "children": { "RLTrainer._checkpoint": { "total": 0.30792526600043857, "count": 2, "self": 0.30792526600043857 } } }, "_update_policy": { "total": 559.0872339609987, "count": 452, "self": 307.1297664630556, "children": { "TorchPPOOptimizer.update": { "total": 251.95746749794307, "count": 22797, "self": 251.95746749794307 } } } } } } }, "trainer_threads": { "total": 1.026999598252587e-06, "count": 1, "self": 1.026999598252587e-06 }, "TrainerController._save_models": { "total": 0.08942030599973805, "count": 1, "self": 0.001378262999423896, "children": { "RLTrainer._checkpoint": { "total": 0.08804204300031415, "count": 1, "self": 0.08804204300031415 } } } } } } }