{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27756866812705994, "min": 0.27756866812705994, "max": 1.4939614534378052, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8322.619140625, "min": 8322.619140625, "max": 45320.81640625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499942.0, "min": 29952.0, "max": 1499942.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499942.0, "min": 29952.0, "max": 1499942.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5789384245872498, "min": -0.0975242480635643, "max": 0.5831009149551392, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.10275268554688, "min": -23.50334358215332, "max": 162.68515014648438, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0047641322016716, "min": -0.00961232464760542, "max": 0.2847445607185364, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3339570760726929, "min": -2.6433892250061035, "max": 68.33869171142578, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06626441871061112, "min": 0.06472257043822624, "max": 0.07405200430449053, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9277018619485556, "min": 0.481576595329626, "max": 1.0788347453926692, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014320910561950296, "min": 0.0001412396246198773, "max": 0.015177880950310887, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20049274786730414, "min": 0.001836115120058405, "max": 0.2276682142546633, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.9522133016761895e-06, "min": 2.9522133016761895e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.1330986223466654e-05, "min": 4.1330986223466654e-05, "max": 0.003821436126188, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10098403809523811, "min": 0.10098403809523811, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4137765333333334, "min": 1.3924565333333336, "max": 2.673812, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010830540571428568, "min": 0.00010830540571428568, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015162756799999995, "min": 0.0015162756799999995, "max": 0.1273938188, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009133702144026756, "min": 0.008654032833874226, "max": 0.4274999797344208, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1278718262910843, "min": 0.12115645408630371, "max": 2.992499828338623, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 341.95348837209303, "min": 325.032967032967, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29408.0, "min": 15984.0, "max": 32524.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5882650993244594, "min": -1.0000000521540642, "max": 1.6081120736978867, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.5907985419035, "min": -30.99220161139965, "max": 146.33819870650768, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5882650993244594, "min": -1.0000000521540642, "max": 1.6081120736978867, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.5907985419035, "min": -30.99220161139965, "max": 146.33819870650768, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03212499187142131, "min": 0.030447889234842526, "max": 8.614150084555149, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7627493009422324, "min": 2.547172557468002, "max": 137.82640135288239, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687142688", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687146127" }, "total": 3438.3760360919996, "count": 1, "self": 0.5281753519993799, "children": { "run_training.setup": { "total": 0.03801211300014984, "count": 1, "self": 0.03801211300014984 }, "TrainerController.start_learning": { "total": 3437.809848627, "count": 1, "self": 2.3642726932612277, "children": { "TrainerController._reset_env": { "total": 3.9950029499996162, "count": 1, "self": 3.9950029499996162 }, "TrainerController.advance": { "total": 3431.3458559627406, "count": 95861, "self": 2.254608118867509, "children": { "env_step": { "total": 2461.6358360100976, "count": 95861, "self": 2283.958441310114, "children": { "SubprocessEnvManager._take_step": { "total": 176.373868001946, "count": 95861, "self": 7.673953184113998, "children": { "TorchPolicy.evaluate": { "total": 168.699914817832, "count": 93805, "self": 168.699914817832 } } }, "workers": { "total": 1.3035266980377855, "count": 95861, "self": 0.0, "children": { "worker_root": { "total": 3429.7770765410396, "count": 95861, "is_parallel": true, "self": 1328.769679007819, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018518609995226143, "count": 1, "is_parallel": true, "self": 0.0006043900002623559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012474709992602584, "count": 8, "is_parallel": true, "self": 0.0012474709992602584 } } }, "UnityEnvironment.step": { "total": 0.05019675099993037, "count": 1, "is_parallel": true, "self": 0.0005551630001718877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005188309996810858, "count": 1, "is_parallel": true, "self": 0.0005188309996810858 }, "communicator.exchange": { "total": 0.04711564199988061, "count": 1, "is_parallel": true, "self": 0.04711564199988061 }, "steps_from_proto": { "total": 0.002007115000196791, "count": 1, "is_parallel": true, "self": 0.0004147039999224944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015924110002742964, "count": 8, "is_parallel": true, "self": 0.0015924110002742964 } } } } } } }, "UnityEnvironment.step": { "total": 2101.0073975332207, "count": 95860, "is_parallel": true, "self": 50.66098508576124, "children": { "UnityEnvironment._generate_step_input": { "total": 36.23023858304714, "count": 95860, "is_parallel": true, "self": 36.23023858304714 }, "communicator.exchange": { "total": 1851.3092562163101, "count": 95860, "is_parallel": true, "self": 1851.3092562163101 }, "steps_from_proto": { "total": 162.80691764810217, "count": 95860, "is_parallel": true, "self": 32.76465410011588, "children": { "_process_rank_one_or_two_observation": { "total": 130.0422635479863, "count": 766880, "is_parallel": true, "self": 130.0422635479863 } } } } } } } } } } }, "trainer_advance": { "total": 967.4554118337755, "count": 95861, "self": 4.311192843687422, "children": { "process_trajectory": { "total": 176.3111501010826, "count": 95861, "self": 175.99676295108384, "children": { "RLTrainer._checkpoint": { "total": 0.3143871499987654, "count": 3, "self": 0.3143871499987654 } } }, "_update_policy": { "total": 786.8330688890055, "count": 688, "self": 504.9381683639567, "children": { "TorchPPOOptimizer.update": { "total": 281.8949005250488, "count": 34221, "self": 281.8949005250488 } } } } } } }, "trainer_threads": { "total": 1.4869992810417898e-06, "count": 1, "self": 1.4869992810417898e-06 }, "TrainerController._save_models": { "total": 0.1047155339992969, "count": 1, "self": 0.001472164999540837, "children": { "RLTrainer._checkpoint": { "total": 0.10324336899975606, "count": 1, "self": 0.10324336899975606 } } } } } } }