{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6008763313293457, "min": 0.6008763313293457, "max": 1.4168304204940796, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18026.2890625, "min": 18026.2890625, "max": 42980.96875, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.21748961508274078, "min": -0.13874301314353943, "max": 0.3224957585334778, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.11231994628906, "min": -32.88209533691406, "max": 84.8163833618164, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005971113685518503, "min": -0.04440906643867493, "max": 0.17266212403774261, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5405473709106445, "min": -11.679584503173828, "max": 41.611572265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06901709031635185, "min": 0.06475357347920814, "max": 0.07248224228064323, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9662392644289259, "min": 0.4942465983702528, "max": 1.0872336342096485, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007830955171373905, "min": 0.00012241740345711843, "max": 0.00903605645193498, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10963337239923467, "min": 0.0017138436483996578, "max": 0.1266174806979489, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.503376070335715e-06, "min": 7.503376070335715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010504726498470002, "min": 0.00010504726498470002, "max": 0.003509336630221199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250109285714289, "min": 0.10250109285714289, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350153000000003, "min": 1.3886848, "max": 2.5697788000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002598591764285715, "min": 0.0002598591764285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003638028470000001, "min": 0.003638028470000001, "max": 0.11700090212, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011427265591919422, "min": 0.011427265591919422, "max": 0.37814801931381226, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15998171269893646, "min": 0.15998171269893646, "max": 2.647036075592041, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 611.9183673469388, "min": 580.3818181818182, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29984.0, "min": 15984.0, "max": 32933.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8164856865697977, "min": -1.0000000521540642, "max": 1.0194726992737164, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.00779864192009, "min": -31.991201654076576, "max": 56.0709984600544, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8164856865697977, "min": -1.0000000521540642, "max": 1.0194726992737164, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.00779864192009, "min": -31.991201654076576, "max": 56.0709984600544, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07260907739424621, "min": 0.06928640403043987, "max": 7.59955011960119, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5578447923180647, "min": 3.345245283591794, "max": 121.59280191361904, "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": "1735836021", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/caodq/anaconda3/envs/newenv/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1735836646" }, "total": 624.480163686, "count": 1, "self": 0.217014781999751, "children": { "run_training.setup": { "total": 0.00772972300001129, "count": 1, "self": 0.00772972300001129 }, "TrainerController.start_learning": { "total": 624.2554191810002, "count": 1, "self": 0.552452653993214, "children": { "TrainerController._reset_env": { "total": 1.1392085110001062, "count": 1, "self": 1.1392085110001062 }, "TrainerController.advance": { "total": 622.530176256007, "count": 63428, "self": 0.5213351860038529, "children": { "env_step": { "total": 403.6887590159931, "count": 63428, "self": 349.9591664129475, "children": { "SubprocessEnvManager._take_step": { "total": 53.389533907051145, "count": 63428, "self": 1.8711925520597106, "children": { "TorchPolicy.evaluate": { "total": 51.518341354991435, "count": 62554, "self": 51.518341354991435 } } }, "workers": { "total": 0.3400586959944576, "count": 63428, "self": 0.0, "children": { "worker_root": { "total": 623.4833541759945, "count": 63428, "is_parallel": true, "self": 312.4717873560155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007211460001599335, "count": 1, "is_parallel": true, "self": 0.00021456800027408462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005065779998858488, "count": 8, "is_parallel": true, "self": 0.0005065779998858488 } } }, "UnityEnvironment.step": { "total": 0.014516319999984262, "count": 1, "is_parallel": true, "self": 0.00021717699996770534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019917700001315097, "count": 1, "is_parallel": true, "self": 0.00019917700001315097 }, "communicator.exchange": { "total": 0.013447305999989112, "count": 1, "is_parallel": true, "self": 0.013447305999989112 }, "steps_from_proto": { "total": 0.0006526600000142935, "count": 1, "is_parallel": true, "self": 0.0001404110000748915, "children": { "_process_rank_one_or_two_observation": { "total": 0.000512248999939402, "count": 8, "is_parallel": true, "self": 0.000512248999939402 } } } } } } }, "UnityEnvironment.step": { "total": 311.01156681997895, "count": 63427, "is_parallel": true, "self": 8.791697976976138, "children": { "UnityEnvironment._generate_step_input": { "total": 5.536975688968369, "count": 63427, "is_parallel": true, "self": 5.536975688968369 }, "communicator.exchange": { "total": 272.75133394401314, "count": 63427, "is_parallel": true, "self": 272.75133394401314 }, "steps_from_proto": { "total": 23.931559210021305, "count": 63427, "is_parallel": true, "self": 5.233702610026967, "children": { "_process_rank_one_or_two_observation": { "total": 18.69785659999434, "count": 507416, "is_parallel": true, "self": 18.69785659999434 } } } } } } } } } } }, "trainer_advance": { "total": 218.32008205401007, "count": 63428, "self": 1.0045632480237146, "children": { "process_trajectory": { "total": 45.12361662998478, "count": 63428, "self": 45.03047525798479, "children": { "RLTrainer._checkpoint": { "total": 0.09314137199999095, "count": 2, "self": 0.09314137199999095 } } }, "_update_policy": { "total": 172.19190217600158, "count": 454, "self": 97.44186038499788, "children": { "TorchPPOOptimizer.update": { "total": 74.7500417910037, "count": 22791, "self": 74.7500417910037 } } } } } } }, "trainer_threads": { "total": 5.129995770403184e-07, "count": 1, "self": 5.129995770403184e-07 }, "TrainerController._save_models": { "total": 0.03358124700025655, "count": 1, "self": 0.0005414050001490978, "children": { "RLTrainer._checkpoint": { "total": 0.033039842000107456, "count": 1, "self": 0.033039842000107456 } } } } } } }