{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.352596640586853, "min": 0.352596640586853, "max": 1.4438633918762207, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10532.7666015625, "min": 10532.7666015625, "max": 43801.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5242827534675598, "min": -0.15232543647289276, "max": 0.5568318963050842, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.226318359375, "min": -36.10112762451172, "max": 154.7992706298828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0017738514579832554, "min": -0.011245288886129856, "max": 0.3378306031227112, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.49135684967041016, "min": -2.9575109481811523, "max": 81.079345703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06509389588332158, "min": 0.06509389588332158, "max": 0.07197656412193153, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9113145423665022, "min": 0.4926972930435354, "max": 1.0577035829243386, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017509505700824473, "min": 0.0005202187562566717, "max": 0.017509505700824473, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24513307981154261, "min": 0.004161750050053373, "max": 0.261881070214383, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.679090297478569e-06, "min": 7.679090297478569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010750726416469996, "min": 0.00010750726416469996, "max": 0.0033829412723530004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025596642857143, "min": 0.1025596642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358353000000001, "min": 1.3691136000000002, "max": 2.5276470000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026571046214285713, "min": 0.00026571046214285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00371994647, "min": 0.00371994647, "max": 0.1127919353, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012241525575518608, "min": 0.011378294788300991, "max": 0.44877880811691284, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17138135433197021, "min": 0.15929612517356873, "max": 3.141451597213745, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 335.35869565217394, "min": 335.35869565217394, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30853.0, "min": 15984.0, "max": 32565.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5776608474552631, "min": -1.0000000521540642, "max": 1.6140636154873804, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.1447979658842, "min": -32.000001668930054, "max": 145.1447979658842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5776608474552631, "min": -1.0000000521540642, "max": 1.6140636154873804, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.1447979658842, "min": -32.000001668930054, "max": 145.1447979658842, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04284386810151931, "min": 0.04284386810151931, "max": 8.549296743236482, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9416358653397765, "min": 3.606773059553234, "max": 136.78874789178371, "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": "1678922190", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1678924315" }, "total": 2125.309630403, "count": 1, "self": 0.49277456599975267, "children": { "run_training.setup": { "total": 0.3357330300000285, "count": 1, "self": 0.3357330300000285 }, "TrainerController.start_learning": { "total": 2124.4811228070002, "count": 1, "self": 1.2732231900035913, "children": { "TrainerController._reset_env": { "total": 8.843219354999974, "count": 1, "self": 8.843219354999974 }, "TrainerController.advance": { "total": 2114.270565774996, "count": 63677, "self": 1.4622285509631183, "children": { "env_step": { "total": 1496.5163646940314, "count": 63677, "self": 1388.630765608039, "children": { "SubprocessEnvManager._take_step": { "total": 107.09315168199248, "count": 63677, "self": 4.674478920987667, "children": { "TorchPolicy.evaluate": { "total": 102.41867276100481, "count": 62554, "self": 102.41867276100481 } } }, "workers": { "total": 0.7924474039998586, "count": 63677, "self": 0.0, "children": { "worker_root": { "total": 2119.658654461017, "count": 63677, "is_parallel": true, "self": 845.986704066017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005844532000082836, "count": 1, "is_parallel": true, "self": 0.003904330000068512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019402020000143239, "count": 8, "is_parallel": true, "self": 0.0019402020000143239 } } }, "UnityEnvironment.step": { "total": 0.0513837070000136, "count": 1, "is_parallel": true, "self": 0.0005448789999036308, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004396599999836326, "count": 1, "is_parallel": true, "self": 0.0004396599999836326 }, "communicator.exchange": { "total": 0.04881509200004075, "count": 1, "is_parallel": true, "self": 0.04881509200004075 }, "steps_from_proto": { "total": 0.001584076000085588, "count": 1, "is_parallel": true, "self": 0.0003718990000152189, "children": { "_process_rank_one_or_two_observation": { "total": 0.001212177000070369, "count": 8, "is_parallel": true, "self": 0.001212177000070369 } } } } } } }, "UnityEnvironment.step": { "total": 1273.6719503949998, "count": 63676, "is_parallel": true, "self": 31.06672961307595, "children": { "UnityEnvironment._generate_step_input": { "total": 22.704181733008454, "count": 63676, "is_parallel": true, "self": 22.704181733008454 }, "communicator.exchange": { "total": 1127.127074955953, "count": 63676, "is_parallel": true, "self": 1127.127074955953 }, "steps_from_proto": { "total": 92.77396409296227, "count": 63676, "is_parallel": true, "self": 19.833332882013565, "children": { "_process_rank_one_or_two_observation": { "total": 72.94063121094871, "count": 509408, "is_parallel": true, "self": 72.94063121094871 } } } } } } } } } } }, "trainer_advance": { "total": 616.2919725300015, "count": 63677, "self": 2.5091048979732022, "children": { "process_trajectory": { "total": 117.79389257802438, "count": 63677, "self": 117.57311557502442, "children": { "RLTrainer._checkpoint": { "total": 0.2207770029999665, "count": 2, "self": 0.2207770029999665 } } }, "_update_policy": { "total": 495.98897505400396, "count": 443, "self": 312.9837423480067, "children": { "TorchPPOOptimizer.update": { "total": 183.0052327059973, "count": 22836, "self": 183.0052327059973 } } } } } } }, "trainer_threads": { "total": 1.030000021273736e-06, "count": 1, "self": 1.030000021273736e-06 }, "TrainerController._save_models": { "total": 0.09411345700027596, "count": 1, "self": 0.0016304280002259475, "children": { "RLTrainer._checkpoint": { "total": 0.09248302900005001, "count": 1, "self": 0.09248302900005001 } } } } } } }