{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28520941734313965, "min": 0.2733217179775238, "max": 1.4976612329483032, "count": 55 }, "Pyramids.Policy.Entropy.sum": { "value": 8611.04296875, "min": 8192.15625, "max": 45433.05078125, "count": 55 }, "Pyramids.Step.mean": { "value": 1649934.0, "min": 29887.0, "max": 1649934.0, "count": 55 }, "Pyramids.Step.sum": { "value": 1649934.0, "min": 29887.0, "max": 1649934.0, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6780844330787659, "min": -0.11254404485225677, "max": 0.7492045164108276, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.54171752929688, "min": -27.12311553955078, "max": 223.26295471191406, "count": 55 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009448010474443436, "min": -0.00471834558993578, "max": 0.3657824397087097, "count": 55 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.654891014099121, "min": -1.2833900451660156, "max": 86.69043731689453, "count": 55 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06847106787975792, "min": 0.06368693173993431, "max": 0.07344740603457686, "count": 55 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9585949503166108, "min": 0.5041755350472555, "max": 1.0606178565358277, "count": 55 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014060317887231662, "min": 0.0001427822268103325, "max": 0.017048526659242013, "count": 55 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19684445042124327, "min": 0.0015706044949136575, "max": 0.24031072343795506, "count": 55 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013649884735754525, "min": 0.00013649884735754525, "max": 0.0002984119005293667, "count": 55 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0019109838630056333, "min": 0.0019109838630056333, "max": 0.003759144946951733, "count": 55 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14549959761904763, "min": 0.14549959761904763, "max": 0.19947063333333334, "count": 55 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.036994366666667, "min": 1.3962944333333334, "max": 2.7075822, "count": 55 }, "Pyramids.Policy.Beta.mean": { "value": 0.004555409802142856, "min": 0.004555409802142856, "max": 0.009947116269999999, "count": 55 }, "Pyramids.Policy.Beta.sum": { "value": 0.06377573722999999, "min": 0.06377573722999999, "max": 0.12531952184, "count": 55 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005777300335466862, "min": 0.005777300335466862, "max": 0.523715615272522, "count": 55 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08088220655918121, "min": 0.08088220655918121, "max": 3.6660094261169434, "count": 55 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.35643564356434, "min": 238.6890756302521, "max": 999.0, "count": 55 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28720.0, "min": 16686.0, "max": 32547.0, "count": 55 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6548239760100842, "min": -0.9999750521965325, "max": 1.7276873870306657, "count": 55 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.48239760100842, "min": -31.99920167028904, "max": 205.5947990566492, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6548239760100842, "min": -0.9999750521965325, "max": 1.7276873870306657, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.48239760100842, "min": -31.99920167028904, "max": 205.5947990566492, "count": 55 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017294968862843235, "min": 0.016094309562634277, "max": 10.216091198079726, "count": 55 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7294968862843234, "min": 1.7294968862843234, "max": 173.67355036735535, "count": 55 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751393608", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751397453" }, "total": 3844.742179635, "count": 1, "self": 0.4779578510006104, "children": { "run_training.setup": { "total": 0.020164239999758138, "count": 1, "self": 0.020164239999758138 }, "TrainerController.start_learning": { "total": 3844.2440575439996, "count": 1, "self": 2.50820090414436, "children": { "TrainerController._reset_env": { "total": 2.1762323789998845, "count": 1, "self": 2.1762323789998845 }, "TrainerController.advance": { "total": 3839.558459502856, "count": 106966, "self": 2.6305624058677495, "children": { "env_step": { "total": 2723.3876206570267, "count": 106966, "self": 2459.9872923110815, "children": { "SubprocessEnvManager._take_step": { "total": 261.9089803479128, "count": 106966, "self": 7.798803249086632, "children": { "TorchPolicy.evaluate": { "total": 254.11017709882617, "count": 104185, "self": 254.11017709882617 } } }, "workers": { "total": 1.4913479980323245, "count": 106965, "self": 0.0, "children": { "worker_root": { "total": 3834.565972089129, "count": 106965, "is_parallel": true, "self": 1574.3750310990636, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018549610003901762, "count": 1, "is_parallel": true, "self": 0.0005791610001324443, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012758000002577319, "count": 8, "is_parallel": true, "self": 0.0012758000002577319 } } }, "UnityEnvironment.step": { "total": 0.05104914099956659, "count": 1, "is_parallel": true, "self": 0.0005734369997298927, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004945559994666837, "count": 1, "is_parallel": true, "self": 0.0004945559994666837 }, "communicator.exchange": { "total": 0.048260178999953496, "count": 1, "is_parallel": true, "self": 0.048260178999953496 }, "steps_from_proto": { "total": 0.0017209690004165168, "count": 1, "is_parallel": true, "self": 0.00035610700069810264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013648619997184142, "count": 8, "is_parallel": true, "self": 0.0013648619997184142 } } } } } } }, "UnityEnvironment.step": { "total": 2260.1909409900654, "count": 106964, "is_parallel": true, "self": 54.10291089801558, "children": { "UnityEnvironment._generate_step_input": { "total": 38.71587965702656, "count": 106964, "is_parallel": true, "self": 38.71587965702656 }, "communicator.exchange": { "total": 2003.4023570450481, "count": 106964, "is_parallel": true, "self": 2003.4023570450481 }, "steps_from_proto": { "total": 163.96979338997517, "count": 106964, "is_parallel": true, "self": 33.74348840165112, "children": { "_process_rank_one_or_two_observation": { "total": 130.22630498832405, "count": 855712, "is_parallel": true, "self": 130.22630498832405 } } } } } } } } } } }, "trainer_advance": { "total": 1113.5402764399614, "count": 106965, "self": 4.7615489370427895, "children": { "process_trajectory": { "total": 213.96929614093278, "count": 106965, "self": 213.64406671093275, "children": { "RLTrainer._checkpoint": { "total": 0.3252294300000358, "count": 3, "self": 0.3252294300000358 } } }, "_update_policy": { "total": 894.8094313619858, "count": 757, "self": 495.0967092089513, "children": { "TorchPPOOptimizer.update": { "total": 399.7127221530345, "count": 38019, "self": 399.7127221530345 } } } } } } }, "trainer_threads": { "total": 1.3760000001639128e-06, "count": 1, "self": 1.3760000001639128e-06 }, "TrainerController._save_models": { "total": 0.001163381999504054, "count": 1, "self": 2.2817999706603587e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0011405639997974504, "count": 1, "self": 0.0011405639997974504 } } } } } } }