{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3846076428890228, "min": 0.3833308815956116, "max": 1.5098246335983276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11655.150390625, "min": 11422.2412109375, "max": 45802.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5818838477134705, "min": -0.10555002838373184, "max": 0.5818838477134705, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 163.50936889648438, "min": -25.332006454467773, "max": 163.50936889648438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024695392698049545, "min": 0.009741031564772129, "max": 0.2150718718767166, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.93940544128418, "min": 2.5229272842407227, "max": 51.83232116699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06807303992098429, "min": 0.06524180654317, "max": 0.07394013747608384, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9530225588937801, "min": 0.49190884980827376, "max": 1.0545428169619604, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015759560995241523, "min": 0.0008012288526890431, "max": 0.015759560995241523, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22063385393338134, "min": 0.007498496669599157, "max": 0.22273432953321998, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.417811813142858e-06, "min": 7.417811813142858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010384936538400001, "min": 0.00010384936538400001, "max": 0.0032551202149599997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247257142857145, "min": 0.10247257142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346160000000003, "min": 1.3886848, "max": 2.4442957, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025700988571428576, "min": 0.00025700988571428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035981384000000004, "min": 0.0035981384000000004, "max": 0.10852549599999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013441706076264381, "min": 0.013441706076264381, "max": 0.38476258516311646, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18818388879299164, "min": 0.18818388879299164, "max": 2.69333815574646, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.56382978723406, "min": 331.56382978723406, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31167.0, "min": 15984.0, "max": 33016.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6292905081259577, "min": -1.0000000521540642, "max": 1.6372344543536503, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.78259827196598, "min": -30.049201622605324, "max": 154.78259827196598, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6292905081259577, "min": -1.0000000521540642, "max": 1.6372344543536503, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.78259827196598, "min": -30.049201622605324, "max": 154.78259827196598, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045566108817154984, "min": 0.045566108817154984, "max": 8.569565658457577, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.328780337629723, "min": 4.185864482540637, "max": 137.11305053532124, "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": "1756033779", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756035970" }, "total": 2190.6587630259996, "count": 1, "self": 0.4754521499994553, "children": { "run_training.setup": { "total": 0.02901185800010353, "count": 1, "self": 0.02901185800010353 }, "TrainerController.start_learning": { "total": 2190.154299018, "count": 1, "self": 1.334541701975013, "children": { "TrainerController._reset_env": { "total": 2.6416640039999493, "count": 1, "self": 2.6416640039999493 }, "TrainerController.advance": { "total": 2186.102888007025, "count": 63772, "self": 1.3463753530977556, "children": { "env_step": { "total": 1542.0807603559792, "count": 63772, "self": 1397.695528086949, "children": { "SubprocessEnvManager._take_step": { "total": 143.57964742903664, "count": 63772, "self": 4.487461024081767, "children": { "TorchPolicy.evaluate": { "total": 139.09218640495487, "count": 62565, "self": 139.09218640495487 } } }, "workers": { "total": 0.8055848399935712, "count": 63772, "self": 0.0, "children": { "worker_root": { "total": 2185.5679823199816, "count": 63772, "is_parallel": true, "self": 898.4433286818878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023612289999164204, "count": 1, "is_parallel": true, "self": 0.0007332099996801844, "children": { "_process_rank_one_or_two_observation": { "total": 0.001628019000236236, "count": 8, "is_parallel": true, "self": 0.001628019000236236 } } }, "UnityEnvironment.step": { "total": 0.04882033499984573, "count": 1, "is_parallel": true, "self": 0.0005025779994412005, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004909250001219334, "count": 1, "is_parallel": true, "self": 0.0004909250001219334 }, "communicator.exchange": { "total": 0.046210541000164085, "count": 1, "is_parallel": true, "self": 0.046210541000164085 }, "steps_from_proto": { "total": 0.0016162910001185082, "count": 1, "is_parallel": true, "self": 0.00032748000012361445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012888109999948938, "count": 8, "is_parallel": true, "self": 0.0012888109999948938 } } } } } } }, "UnityEnvironment.step": { "total": 1287.1246536380938, "count": 63771, "is_parallel": true, "self": 31.25416772613744, "children": { "UnityEnvironment._generate_step_input": { "total": 22.63729023499286, "count": 63771, "is_parallel": true, "self": 22.63729023499286 }, "communicator.exchange": { "total": 1137.4952609380114, "count": 63771, "is_parallel": true, "self": 1137.4952609380114 }, "steps_from_proto": { "total": 95.73793473895216, "count": 63771, "is_parallel": true, "self": 19.03209970907278, "children": { "_process_rank_one_or_two_observation": { "total": 76.70583502987938, "count": 510168, "is_parallel": true, "self": 76.70583502987938 } } } } } } } } } } }, "trainer_advance": { "total": 642.6757522979478, "count": 63772, "self": 2.6000749130355416, "children": { "process_trajectory": { "total": 122.3217346359138, "count": 63772, "self": 122.13009232691365, "children": { "RLTrainer._checkpoint": { "total": 0.19164230900014445, "count": 2, "self": 0.19164230900014445 } } }, "_update_policy": { "total": 517.7539427489985, "count": 447, "self": 289.45424722399116, "children": { "TorchPPOOptimizer.update": { "total": 228.29969552500734, "count": 22857, "self": 228.29969552500734 } } } } } } }, "trainer_threads": { "total": 7.990001904545352e-07, "count": 1, "self": 7.990001904545352e-07 }, "TrainerController._save_models": { "total": 0.07520450599986361, "count": 1, "self": 0.0013040220001130365, "children": { "RLTrainer._checkpoint": { "total": 0.07390048399975058, "count": 1, "self": 0.07390048399975058 } } } } } } }