{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16062022745609283, "min": 0.14916810393333435, "max": 1.4874749183654785, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4782.6279296875, "min": 4479.81640625, "max": 45124.0390625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999954.0, "min": 29952.0, "max": 2999954.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999954.0, "min": 29952.0, "max": 2999954.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7424909472465515, "min": -0.11016630381345749, "max": 0.8764814138412476, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 219.77731323242188, "min": -26.32974624633789, "max": 268.20330810546875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010064886882901192, "min": -0.039204683154821396, "max": 0.29718294739723206, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9792065620422363, "min": -11.134129524230957, "max": 70.43235778808594, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06459761918328391, "min": 0.06459761918328391, "max": 0.07492844989733298, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9043666685659748, "min": 0.505245195859615, "max": 1.1239267484599946, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015460626827830098, "min": 0.00013524580038463437, "max": 0.01742398080597114, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21644877558962136, "min": 0.0016229496046156124, "max": 0.2613597120895671, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4420138050761899e-06, "min": 1.4420138050761899e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.018819327106666e-05, "min": 2.018819327106666e-05, "max": 0.0037250539583153666, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004806380952381, "min": 0.1004806380952381, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067289333333335, "min": 1.3845131666666668, "max": 2.7375122333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.8015745714285704e-05, "min": 5.8015745714285704e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008122204399999999, "min": 0.0008122204399999999, "max": 0.12417429487, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006761837750673294, "min": 0.006591344717890024, "max": 0.3868617117404938, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09466572850942612, "min": 0.08891013264656067, "max": 2.7080318927764893, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.64341085271317, "min": 205.44897959183675, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29882.0, "min": 15984.0, "max": 32569.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7523999857949093, "min": -1.0000000521540642, "max": 1.780751865497209, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 224.3071981817484, "min": -31.998001664876938, "max": 263.546398460865, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7523999857949093, "min": -1.0000000521540642, "max": 1.780751865497209, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 224.3071981817484, "min": -31.998001664876938, "max": 263.546398460865, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016589596277185592, "min": 0.015110047187418613, "max": 7.286261928267777, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.123468323479756, "min": 2.024178839252272, "max": 116.58019085228443, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709560169", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709567417" }, "total": 7248.2344472800005, "count": 1, "self": 0.47782015899974795, "children": { "run_training.setup": { "total": 0.050687829000025886, "count": 1, "self": 0.050687829000025886 }, "TrainerController.start_learning": { "total": 7247.705939292001, "count": 1, "self": 4.27681587976349, "children": { "TrainerController._reset_env": { "total": 2.4904635200000484, "count": 1, "self": 2.4904635200000484 }, "TrainerController.advance": { "total": 7240.847285311236, "count": 194597, "self": 4.353021463503865, "children": { "env_step": { "total": 5327.526908300961, "count": 194597, "self": 4933.80991470468, "children": { "SubprocessEnvManager._take_step": { "total": 391.14543661222297, "count": 194597, "self": 14.47117661809716, "children": { "TorchPolicy.evaluate": { "total": 376.6742599941258, "count": 187550, "self": 376.6742599941258 } } }, "workers": { "total": 2.571556984058134, "count": 194597, "self": 0.0, "children": { "worker_root": { "total": 7232.078320825932, "count": 194597, "is_parallel": true, "self": 2651.5202296840434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002063921999933882, "count": 1, "is_parallel": true, "self": 0.000617229000226871, "children": { "_process_rank_one_or_two_observation": { "total": 0.001446692999707011, "count": 8, "is_parallel": true, "self": 0.001446692999707011 } } }, "UnityEnvironment.step": { "total": 0.04826579399991715, "count": 1, "is_parallel": true, "self": 0.0005725229998461145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004736240000511316, "count": 1, "is_parallel": true, "self": 0.0004736240000511316 }, "communicator.exchange": { "total": 0.04557797600000413, "count": 1, "is_parallel": true, "self": 0.04557797600000413 }, "steps_from_proto": { "total": 0.0016416710000157764, "count": 1, "is_parallel": true, "self": 0.0003458419998878526, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012958290001279238, "count": 8, "is_parallel": true, "self": 0.0012958290001279238 } } } } } } }, "UnityEnvironment.step": { "total": 4580.558091141888, "count": 194596, "is_parallel": true, "self": 107.72708973078534, "children": { "UnityEnvironment._generate_step_input": { "total": 74.28047602401352, "count": 194596, "is_parallel": true, "self": 74.28047602401352 }, "communicator.exchange": { "total": 4095.1915789779614, "count": 194596, "is_parallel": true, "self": 4095.1915789779614 }, "steps_from_proto": { "total": 303.3589464091283, "count": 194596, "is_parallel": true, "self": 60.273273000197605, "children": { "_process_rank_one_or_two_observation": { "total": 243.0856734089307, "count": 1556768, "is_parallel": true, "self": 243.0856734089307 } } } } } } } } } } }, "trainer_advance": { "total": 1908.9673555467718, "count": 194597, "self": 8.368508516836755, "children": { "process_trajectory": { "total": 388.75959551591814, "count": 194597, "self": 388.1522410249172, "children": { "RLTrainer._checkpoint": { "total": 0.6073544910009332, "count": 6, "self": 0.6073544910009332 } } }, "_update_policy": { "total": 1511.839251514017, "count": 1389, "self": 884.384923058898, "children": { "TorchPPOOptimizer.update": { "total": 627.4543284551189, "count": 68397, "self": 627.4543284551189 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.09137364300113404, "count": 1, "self": 0.0016801950023364043, "children": { "RLTrainer._checkpoint": { "total": 0.08969344799879764, "count": 1, "self": 0.08969344799879764 } } } } } } }