{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6756361126899719, "min": 0.6701516509056091, "max": 1.4935383796691895, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20333.9453125, "min": 20115.271484375, "max": 45307.98046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29974.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29974.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18971240520477295, "min": -0.11628411710262299, "max": 0.18971240520477295, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 48.18695068359375, "min": -27.908187866210938, "max": 48.18695068359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.017311885952949524, "min": -0.017311885952949524, "max": 0.3339952826499939, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.397219181060791, "min": -4.397219181060791, "max": 79.82487487792969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06804686577088023, "min": 0.06244572261530101, "max": 0.07271378252218956, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9526561207923233, "min": 0.5693039985443198, "max": 1.0337674864276778, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009808101011064742, "min": 4.252900801812795e-05, "max": 0.009808101011064742, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1373134141549064, "min": 0.0005528771042356633, "max": 0.1373134141549064, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.687318866164289e-06, "min": 7.687318866164289e-06, "max": 0.000294771226742925, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010762246412630004, "min": 0.00010762246412630004, "max": 0.0033760123746625994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256240714285715, "min": 0.10256240714285715, "max": 0.198257075, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358737000000001, "min": 1.4358737000000001, "max": 2.4253374, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026598447357142863, "min": 0.00026598447357142863, "max": 0.009825881792500001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003723782630000001, "min": 0.003723782630000001, "max": 0.11255120626000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012228773906826973, "min": 0.012228773906826973, "max": 0.3726975917816162, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17120283842086792, "min": 0.17120283842086792, "max": 2.9815807342529297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 651.8695652173913, "min": 650.5744680851063, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29986.0, "min": 17412.0, "max": 33091.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8262260561080083, "min": -0.9999862593309633, "max": 0.8262260561080083, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 38.00639858096838, "min": -31.9992016851902, "max": 38.00639858096838, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8262260561080083, "min": -0.9999862593309633, "max": 0.8262260561080083, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 38.00639858096838, "min": -31.9992016851902, "max": 38.00639858096838, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08246177341156315, "min": 0.08246177341156315, "max": 7.827282040431681, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.793241576931905, "min": 3.793241576931905, "max": 140.89107672777027, "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": "1723097018", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723099058" }, "total": 2039.6740329119998, "count": 1, "self": 0.4759332749997611, "children": { "run_training.setup": { "total": 0.05165100399995026, "count": 1, "self": 0.05165100399995026 }, "TrainerController.start_learning": { "total": 2039.146448633, "count": 1, "self": 1.417873042025576, "children": { "TrainerController._reset_env": { "total": 2.0833010549999926, "count": 1, "self": 2.0833010549999926 }, "TrainerController.advance": { "total": 2035.5592469469746, "count": 63118, "self": 1.516181049967372, "children": { "env_step": { "total": 1401.0235454000162, "count": 63118, "self": 1264.1000981470065, "children": { "SubprocessEnvManager._take_step": { "total": 136.0496659569909, "count": 63118, "self": 4.664039991971663, "children": { "TorchPolicy.evaluate": { "total": 131.38562596501924, "count": 62571, "self": 131.38562596501924 } } }, "workers": { "total": 0.8737812960187057, "count": 63118, "self": 0.0, "children": { "worker_root": { "total": 2034.123707210017, "count": 63118, "is_parallel": true, "self": 895.2181351230279, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020446720000109053, "count": 1, "is_parallel": true, "self": 0.0006199140002536296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014247579997572757, "count": 8, "is_parallel": true, "self": 0.0014247579997572757 } } }, "UnityEnvironment.step": { "total": 0.04945018400007939, "count": 1, "is_parallel": true, "self": 0.0006115370000543408, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004287250000061249, "count": 1, "is_parallel": true, "self": 0.0004287250000061249 }, "communicator.exchange": { "total": 0.04678344299998116, "count": 1, "is_parallel": true, "self": 0.04678344299998116 }, "steps_from_proto": { "total": 0.0016264790000377616, "count": 1, "is_parallel": true, "self": 0.0003340649998335721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012924140002041895, "count": 8, "is_parallel": true, "self": 0.0012924140002041895 } } } } } } }, "UnityEnvironment.step": { "total": 1138.9055720869892, "count": 63117, "is_parallel": true, "self": 33.51948442598314, "children": { "UnityEnvironment._generate_step_input": { "total": 23.53362026202126, "count": 63117, "is_parallel": true, "self": 23.53362026202126 }, "communicator.exchange": { "total": 981.8826445739744, "count": 63117, "is_parallel": true, "self": 981.8826445739744 }, "steps_from_proto": { "total": 99.96982282501051, "count": 63117, "is_parallel": true, "self": 20.610159356888403, "children": { "_process_rank_one_or_two_observation": { "total": 79.35966346812211, "count": 504936, "is_parallel": true, "self": 79.35966346812211 } } } } } } } } } } }, "trainer_advance": { "total": 633.0195204969909, "count": 63118, "self": 2.519143280954154, "children": { "process_trajectory": { "total": 126.85651098603148, "count": 63118, "self": 126.6546695240313, "children": { "RLTrainer._checkpoint": { "total": 0.20184146200017494, "count": 2, "self": 0.20184146200017494 } } }, "_update_policy": { "total": 503.6438662300053, "count": 439, "self": 298.25273636900215, "children": { "TorchPPOOptimizer.update": { "total": 205.39112986100315, "count": 22839, "self": 205.39112986100315 } } } } } } }, "trainer_threads": { "total": 8.829997568682302e-07, "count": 1, "self": 8.829997568682302e-07 }, "TrainerController._save_models": { "total": 0.08602670600021156, "count": 1, "self": 0.0015569390002383443, "children": { "RLTrainer._checkpoint": { "total": 0.08446976699997322, "count": 1, "self": 0.08446976699997322 } } } } } } }