{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.557181179523468, "min": 0.557181179523468, "max": 1.5060040950775146, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 16813.5, "min": 16813.5, "max": 45686.140625, "count": 23 }, "Pyramids.Step.mean": { "value": 689934.0, "min": 29952.0, "max": 689934.0, "count": 23 }, "Pyramids.Step.sum": { "value": 689934.0, "min": 29952.0, "max": 689934.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32283714413642883, "min": -0.10187789052724838, "max": 0.32283714413642883, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.58332824707031, "min": -24.654449462890625, "max": 84.58332824707031, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03935253247618675, "min": -0.03168679028749466, "max": 0.20260284841060638, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.31036376953125, "min": -8.270252227783203, "max": 48.82728576660156, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0707834079540113, "min": 0.06361945722814967, "max": 0.07400125726998899, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.990967711356158, "min": 0.4984452874114036, "max": 1.036017601779846, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013350877895434331, "min": 0.0003163296860552185, "max": 0.014211556315688366, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18691229053608063, "min": 0.003795956232662622, "max": 0.21317334473532548, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.10546065192449e-05, "min": 1.10546065192449e-05, "max": 0.00029307232883983667, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00015476449126942862, "min": 0.00015476449126942862, "max": 0.0034839301386899993, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10368483673469386, "min": 0.10368483673469386, "max": 0.19769077551020411, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.451587714285714, "min": 1.3838354285714287, "max": 2.4710064285714286, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.0003781151897959185, "min": 0.0003781151897959185, "max": 0.00976930847346939, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.005293612657142859, "min": 0.005293612657142859, "max": 0.11614486899999998, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012790570966899395, "min": 0.012790570966899395, "max": 0.30326637625694275, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17906799912452698, "min": 0.17906799912452698, "max": 2.1228647232055664, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 467.34375, "min": 467.34375, "max": 999.0, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29910.0, "min": 15984.0, "max": 32673.0, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3138405915815383, "min": -1.0000000521540642, "max": 1.3138405915815383, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.08579786121845, "min": -31.998801693320274, "max": 84.08579786121845, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3138405915815383, "min": -1.0000000521540642, "max": 1.3138405915815383, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.08579786121845, "min": -31.998801693320274, "max": 84.08579786121845, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.061312550617913075, "min": 0.061312550617913075, "max": 6.3588480753824115, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 3.924003239546437, "min": 3.924003239546437, "max": 101.74156920611858, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793635844", "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": "1793637151" }, "total": 1307.426257654, "count": 1, "self": 0.37280885299992406, "children": { "run_training.setup": { "total": 0.027770224000050803, "count": 1, "self": 0.027770224000050803 }, "TrainerController.start_learning": { "total": 1307.025678577, "count": 1, "self": 1.2158832899915524, "children": { "TrainerController._reset_env": { "total": 2.403001993000089, "count": 1, "self": 2.403001993000089 }, "TrainerController.advance": { "total": 1303.3230108920084, "count": 44391, "self": 1.2086046889958197, "children": { "env_step": { "total": 844.6424052549683, "count": 44391, "self": 719.0867009579533, "children": { "SubprocessEnvManager._take_step": { "total": 124.81462221999777, "count": 44391, "self": 3.8264751510216684, "children": { "TorchPolicy.evaluate": { "total": 120.9881470689761, "count": 43818, "self": 120.9881470689761 } } }, "workers": { "total": 0.741082077017154, "count": 44391, "self": 0.0, "children": { "worker_root": { "total": 1305.0045698869965, "count": 44391, "is_parallel": true, "self": 664.6295999740382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002129866000132097, "count": 1, "is_parallel": true, "self": 0.0006419960004677705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014878699996643263, "count": 8, "is_parallel": true, "self": 0.0014878699996643263 } } }, "UnityEnvironment.step": { "total": 0.04172773799996321, "count": 1, "is_parallel": true, "self": 0.00036809900007028773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002899010000874114, "count": 1, "is_parallel": true, "self": 0.0002899010000874114 }, "communicator.exchange": { "total": 0.03855173799979639, "count": 1, "is_parallel": true, "self": 0.03855173799979639 }, "steps_from_proto": { "total": 0.002518000000009124, "count": 1, "is_parallel": true, "self": 0.0002787369999168732, "children": { "_process_rank_one_or_two_observation": { "total": 0.002239263000092251, "count": 8, "is_parallel": true, "self": 0.002239263000092251 } } } } } } }, "UnityEnvironment.step": { "total": 640.3749699129582, "count": 44390, "is_parallel": true, "self": 16.58800655891696, "children": { "UnityEnvironment._generate_step_input": { "total": 10.562764812029855, "count": 44390, "is_parallel": true, "self": 10.562764812029855 }, "communicator.exchange": { "total": 568.2271373140027, "count": 44390, "is_parallel": true, "self": 568.2271373140027 }, "steps_from_proto": { "total": 44.99706122800876, "count": 44390, "is_parallel": true, "self": 10.09013696007105, "children": { "_process_rank_one_or_two_observation": { "total": 34.90692426793771, "count": 355120, "is_parallel": true, "self": 34.90692426793771 } } } } } } } } } } }, "trainer_advance": { "total": 457.4720009480443, "count": 44391, "self": 2.358980212046845, "children": { "process_trajectory": { "total": 78.59222453499615, "count": 44391, "self": 78.48359993599615, "children": { "RLTrainer._checkpoint": { "total": 0.10862459899999521, "count": 1, "self": 0.10862459899999521 } } }, "_update_policy": { "total": 376.5207962010013, "count": 312, "self": 198.07001549501115, "children": { "TorchPPOOptimizer.update": { "total": 178.45078070599016, "count": 15972, "self": 178.45078070599016 } } } } } } }, "trainer_threads": { "total": 1.0099997780343983e-06, "count": 1, "self": 1.0099997780343983e-06 }, "TrainerController._save_models": { "total": 0.08378139200021906, "count": 1, "self": 0.0010219620003226737, "children": { "RLTrainer._checkpoint": { "total": 0.08275942999989638, "count": 1, "self": 0.08275942999989638 } } } } } } }