{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4246979057788849, "min": 0.4246979057788849, "max": 1.4495248794555664, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12815.68359375, "min": 12815.68359375, "max": 43972.78515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6053388118743896, "min": -0.10743533819913864, "max": 0.6053388118743896, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.73223876953125, "min": -25.999351501464844, "max": 173.73223876953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028064681217074394, "min": 0.010141970589756966, "max": 0.35711684823036194, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.054563522338867, "min": 2.46449875831604, "max": 86.0651626586914, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06874954850701173, "min": 0.06598765249181467, "max": 0.0743717322073367, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9624936790981642, "min": 0.4997402624838956, "max": 1.0566421938648074, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014748143734842806, "min": 0.00045146689069620194, "max": 0.016088257654013838, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2064740122877993, "min": 0.006320536469746827, "max": 0.24132386481020757, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.387747537449998e-06, "min": 7.387747537449998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010342846552429996, "min": 0.00010342846552429996, "max": 0.0035092205302598993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246255000000003, "min": 0.10246255000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344757000000004, "min": 1.3886848, "max": 2.5697401000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025600874499999996, "min": 0.00025600874499999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003584122429999999, "min": 0.003584122429999999, "max": 0.11699703599000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01096817385405302, "min": 0.01096817385405302, "max": 0.5842375159263611, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15355443954467773, "min": 0.15355443954467773, "max": 4.089662551879883, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 305.05940594059405, "min": 305.05940594059405, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30811.0, "min": 15984.0, "max": 33242.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6140859753638506, "min": -1.0000000521540642, "max": 1.6198649888858199, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.40859753638506, "min": -30.552001655101776, "max": 161.40859753638506, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6140859753638506, "min": -1.0000000521540642, "max": 1.6198649888858199, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.40859753638506, "min": -30.552001655101776, "max": 161.40859753638506, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03514394163124962, "min": 0.03514394163124962, "max": 12.490680631250143, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.514394163124962, "min": 3.3604462776202126, "max": 199.8508901000023, "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": "1742740339", "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": "1742742647" }, "total": 2307.457171989, "count": 1, "self": 1.1683387050006786, "children": { "run_training.setup": { "total": 0.02748682500009636, "count": 1, "self": 0.02748682500009636 }, "TrainerController.start_learning": { "total": 2306.2613464589995, "count": 1, "self": 1.357832960052292, "children": { "TrainerController._reset_env": { "total": 2.9890709610001522, "count": 1, "self": 2.9890709610001522 }, "TrainerController.advance": { "total": 2301.7845704619476, "count": 63746, "self": 1.4202328849205514, "children": { "env_step": { "total": 1606.8572314399958, "count": 63746, "self": 1451.68252684904, "children": { "SubprocessEnvManager._take_step": { "total": 154.41913720492744, "count": 63746, "self": 4.618161153992105, "children": { "TorchPolicy.evaluate": { "total": 149.80097605093533, "count": 62555, "self": 149.80097605093533 } } }, "workers": { "total": 0.7555673860283605, "count": 63746, "self": 0.0, "children": { "worker_root": { "total": 2300.9929063470418, "count": 63746, "is_parallel": true, "self": 963.9034362730806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003952338000090094, "count": 1, "is_parallel": true, "self": 0.002235140000266256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017171979998238385, "count": 8, "is_parallel": true, "self": 0.0017171979998238385 } } }, "UnityEnvironment.step": { "total": 0.04776223399994706, "count": 1, "is_parallel": true, "self": 0.0005171089997020317, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047591800012014573, "count": 1, "is_parallel": true, "self": 0.00047591800012014573 }, "communicator.exchange": { "total": 0.0451615550000497, "count": 1, "is_parallel": true, "self": 0.0451615550000497 }, "steps_from_proto": { "total": 0.001607652000075177, "count": 1, "is_parallel": true, "self": 0.0003372170006059605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012704349994692166, "count": 8, "is_parallel": true, "self": 0.0012704349994692166 } } } } } } }, "UnityEnvironment.step": { "total": 1337.0894700739611, "count": 63745, "is_parallel": true, "self": 32.45782842912354, "children": { "UnityEnvironment._generate_step_input": { "total": 23.85800401995607, "count": 63745, "is_parallel": true, "self": 23.85800401995607 }, "communicator.exchange": { "total": 1180.243897723992, "count": 63745, "is_parallel": true, "self": 1180.243897723992 }, "steps_from_proto": { "total": 100.52973990088958, "count": 63745, "is_parallel": true, "self": 20.429761144052236, "children": { "_process_rank_one_or_two_observation": { "total": 80.09997875683734, "count": 509960, "is_parallel": true, "self": 80.09997875683734 } } } } } } } } } } }, "trainer_advance": { "total": 693.5071061370315, "count": 63746, "self": 2.60604447602077, "children": { "process_trajectory": { "total": 131.0641054040118, "count": 63746, "self": 130.76040726301176, "children": { "RLTrainer._checkpoint": { "total": 0.3036981410000408, "count": 2, "self": 0.3036981410000408 } } }, "_update_policy": { "total": 559.836956256999, "count": 451, "self": 310.51730274994975, "children": { "TorchPPOOptimizer.update": { "total": 249.31965350704922, "count": 22854, "self": 249.31965350704922 } } } } } } }, "trainer_threads": { "total": 1.1519996405695565e-06, "count": 1, "self": 1.1519996405695565e-06 }, "TrainerController._save_models": { "total": 0.129870923999988, "count": 1, "self": 0.0022372020002876525, "children": { "RLTrainer._checkpoint": { "total": 0.12763372199970036, "count": 1, "self": 0.12763372199970036 } } } } } } }