{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28883060812950134, "min": 0.27670609951019287, "max": 1.3393031358718872, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8697.267578125, "min": 8199.35546875, "max": 40629.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29987.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29987.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5920275449752808, "min": -0.10997747629880905, "max": 0.5984733700752258, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 166.3597412109375, "min": -26.50457191467285, "max": 171.16339111328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008805823512375355, "min": -0.021404096856713295, "max": 0.43955281376838684, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4744362831115723, "min": -5.757701873779297, "max": 104.61357116699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0693190728143185, "min": 0.06362067809185282, "max": 0.07526460114940844, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9704670194004589, "min": 0.6077242824256491, "max": 1.0537044160917182, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015503921673136847, "min": 0.00022282926161088784, "max": 0.016107427250106065, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21705490342391587, "min": 0.002896780400941542, "max": 0.2255039815014849, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.588104613521429e-06, "min": 7.588104613521429e-06, "max": 0.0002948037017321, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010623346458930001, "min": 0.00010623346458930001, "max": 0.0036319579893473995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025293357142857, "min": 0.1025293357142857, "max": 0.19826790000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354106999999998, "min": 1.4354106999999998, "max": 2.6106526, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626806378571429, "min": 0.0002626806378571429, "max": 0.00982696321, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003677528930000001, "min": 0.003677528930000001, "max": 0.12108419473999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013672798871994019, "min": 0.013672798871994019, "max": 0.5140568017959595, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19141918420791626, "min": 0.19141918420791626, "max": 4.626511096954346, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 322.3333333333333, "min": 322.3333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29977.0, "min": 16786.0, "max": 32954.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.613137619629983, "min": -0.9999936006722911, "max": 1.613137619629983, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.02179862558842, "min": -31.996001660823822, "max": 150.02179862558842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.613137619629983, "min": -0.9999936006722911, "max": 1.613137619629983, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.02179862558842, "min": -31.996001660823822, "max": 150.02179862558842, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04540157569347009, "min": 0.04540157569347009, "max": 10.639177565627238, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.222346539492719, "min": 4.086957166597131, "max": 180.86601861566305, "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": "1727536271", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727538866" }, "total": 2594.561626419, "count": 1, "self": 0.8337333979993673, "children": { "run_training.setup": { "total": 0.05596249600000647, "count": 1, "self": 0.05596249600000647 }, "TrainerController.start_learning": { "total": 2593.6719305250003, "count": 1, "self": 1.8898117079602343, "children": { "TrainerController._reset_env": { "total": 2.559048544999996, "count": 1, "self": 2.559048544999996 }, "TrainerController.advance": { "total": 2589.0958416020403, "count": 63985, "self": 1.9188152800879834, "children": { "env_step": { "total": 1853.9701390419455, "count": 63985, "self": 1661.212839537951, "children": { "SubprocessEnvManager._take_step": { "total": 191.6142889349842, "count": 63985, "self": 5.614981320963125, "children": { "TorchPolicy.evaluate": { "total": 185.99930761402106, "count": 62566, "self": 185.99930761402106 } } }, "workers": { "total": 1.143010569010471, "count": 63985, "self": 0.0, "children": { "worker_root": { "total": 2587.0884549929897, "count": 63985, "is_parallel": true, "self": 1073.0464266320332, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020746280000025763, "count": 1, "is_parallel": true, "self": 0.0006929760000389251, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013816519999636512, "count": 8, "is_parallel": true, "self": 0.0013816519999636512 } } }, "UnityEnvironment.step": { "total": 0.05452750000000606, "count": 1, "is_parallel": true, "self": 0.0007062880000034966, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004924600000322243, "count": 1, "is_parallel": true, "self": 0.0004924600000322243 }, "communicator.exchange": { "total": 0.05157453900000064, "count": 1, "is_parallel": true, "self": 0.05157453900000064 }, "steps_from_proto": { "total": 0.0017542129999696954, "count": 1, "is_parallel": true, "self": 0.0003895080000120288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013647049999576666, "count": 8, "is_parallel": true, "self": 0.0013647049999576666 } } } } } } }, "UnityEnvironment.step": { "total": 1514.0420283609565, "count": 63984, "is_parallel": true, "self": 38.47304655993935, "children": { "UnityEnvironment._generate_step_input": { "total": 25.663260065041868, "count": 63984, "is_parallel": true, "self": 25.663260065041868 }, "communicator.exchange": { "total": 1338.5141555439584, "count": 63984, "is_parallel": true, "self": 1338.5141555439584 }, "steps_from_proto": { "total": 111.39156619201685, "count": 63984, "is_parallel": true, "self": 24.47425635603946, "children": { "_process_rank_one_or_two_observation": { "total": 86.91730983597739, "count": 511872, "is_parallel": true, "self": 86.91730983597739 } } } } } } } } } } }, "trainer_advance": { "total": 733.2068872800069, "count": 63985, "self": 3.570381476999273, "children": { "process_trajectory": { "total": 142.95335897300583, "count": 63985, "self": 142.65571064300616, "children": { "RLTrainer._checkpoint": { "total": 0.2976483299996744, "count": 2, "self": 0.2976483299996744 } } }, "_update_policy": { "total": 586.6831468300018, "count": 458, "self": 330.24770672692625, "children": { "TorchPPOOptimizer.update": { "total": 256.4354401030755, "count": 22821, "self": 256.4354401030755 } } } } } } }, "trainer_threads": { "total": 1.4289998944150284e-06, "count": 1, "self": 1.4289998944150284e-06 }, "TrainerController._save_models": { "total": 0.12722724099967309, "count": 1, "self": 0.0029598639998766885, "children": { "RLTrainer._checkpoint": { "total": 0.1242673769997964, "count": 1, "self": 0.1242673769997964 } } } } } } }