{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39763304591178894, "min": 0.39763304591178894, "max": 1.4810948371887207, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12011.69921875, "min": 12011.69921875, "max": 44930.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5478923320770264, "min": -0.08867903053760529, "max": 0.6088473200798035, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.76617431640625, "min": -21.371646881103516, "max": 174.13034057617188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.09921073168516159, "min": -0.009514015167951584, "max": 0.31323057413101196, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 27.481372833251953, "min": -2.6353821754455566, "max": 75.80179595947266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07012315097202554, "min": 0.06526013562272834, "max": 0.0751627643660483, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0518472645803831, "min": 0.5250587687722605, "max": 1.0522787011246761, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01663183043201095, "min": 0.0009126936647057585, "max": 0.01663183043201095, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24947745648016426, "min": 0.01277771130588062, "max": 0.24947745648016426, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.523357492246669e-06, "min": 7.523357492246669e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011285036238370004, "min": 0.00011285036238370004, "max": 0.0036085440971519987, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250775333333335, "min": 0.10250775333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376163000000003, "min": 1.3886848, "max": 2.5274666999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026052455800000014, "min": 0.00026052455800000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003907868370000002, "min": 0.003907868370000002, "max": 0.12029451520000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016426868736743927, "min": 0.016426868736743927, "max": 0.445832222700119, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2464030385017395, "min": 0.24308258295059204, "max": 3.1208255290985107, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.4222222222222, "min": 299.2247191011236, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33158.0, "min": 15984.0, "max": 34648.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.495310091821665, "min": -1.0000000521540642, "max": 1.7007752600010861, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.0825981721282, "min": -29.925801545381546, "max": 156.24819799512625, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.495310091821665, "min": -1.0000000521540642, "max": 1.7007752600010861, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.0825981721282, "min": -29.925801545381546, "max": 156.24819799512625, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06342705238997685, "min": 0.05408587265273117, "max": 8.55563797056675, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.64500766270794, "min": 4.813642666093074, "max": 136.890207529068, "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": "1682278572", "python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]", "command_line_arguments": "/home/owner/Documents/venv/unit5_deeprl/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": "1682279908" }, "total": 1336.0309495769998, "count": 1, "self": 0.2688991249999617, "children": { "run_training.setup": { "total": 0.012596594999877198, "count": 1, "self": 0.012596594999877198 }, "TrainerController.start_learning": { "total": 1335.749453857, "count": 1, "self": 1.2406294040065404, "children": { "TrainerController._reset_env": { "total": 3.446223214000156, "count": 1, "self": 3.446223214000156 }, "TrainerController.advance": { "total": 1330.986499268993, "count": 63906, "self": 1.1568209799183933, "children": { "env_step": { "total": 860.023587419061, "count": 63906, "self": 758.5187796660985, "children": { "SubprocessEnvManager._take_step": { "total": 100.71767644298302, "count": 63906, "self": 3.3256034849384832, "children": { "TorchPolicy.evaluate": { "total": 97.39207295804454, "count": 62555, "self": 97.39207295804454 } } }, "workers": { "total": 0.7871313099794861, "count": 63906, "self": 0.0, "children": { "worker_root": { "total": 1334.1012056280283, "count": 63906, "is_parallel": true, "self": 654.8008528519763, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014226690000214148, "count": 1, "is_parallel": true, "self": 0.00038762699978178716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010350420002396277, "count": 8, "is_parallel": true, "self": 0.0010350420002396277 } } }, "UnityEnvironment.step": { "total": 0.026039760000003298, "count": 1, "is_parallel": true, "self": 0.0003213570003026689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019167099981132196, "count": 1, "is_parallel": true, "self": 0.00019167099981132196 }, "communicator.exchange": { "total": 0.024722418000010293, "count": 1, "is_parallel": true, "self": 0.024722418000010293 }, "steps_from_proto": { "total": 0.0008043139998790139, "count": 1, "is_parallel": true, "self": 0.00021809199961353443, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005862220002654794, "count": 8, "is_parallel": true, "self": 0.0005862220002654794 } } } } } } }, "UnityEnvironment.step": { "total": 679.300352776052, "count": 63905, "is_parallel": true, "self": 20.730948805075286, "children": { "UnityEnvironment._generate_step_input": { "total": 12.562124989925223, "count": 63905, "is_parallel": true, "self": 12.562124989925223 }, "communicator.exchange": { "total": 587.7255172520267, "count": 63905, "is_parallel": true, "self": 587.7255172520267 }, "steps_from_proto": { "total": 58.281761729024765, "count": 63905, "is_parallel": true, "self": 12.515688130148646, "children": { "_process_rank_one_or_two_observation": { "total": 45.76607359887612, "count": 511240, "is_parallel": true, "self": 45.76607359887612 } } } } } } } } } } }, "trainer_advance": { "total": 469.8060908700136, "count": 63906, "self": 2.060754821026194, "children": { "process_trajectory": { "total": 80.93437049099043, "count": 63906, "self": 80.77069258199026, "children": { "RLTrainer._checkpoint": { "total": 0.16367790900017098, "count": 2, "self": 0.16367790900017098 } } }, "_update_policy": { "total": 386.81096555799695, "count": 454, "self": 231.58154099101876, "children": { "TorchPPOOptimizer.update": { "total": 155.2294245669782, "count": 22779, "self": 155.2294245669782 } } } } } } }, "trainer_threads": { "total": 7.940002433315385e-07, "count": 1, "self": 7.940002433315385e-07 }, "TrainerController._save_models": { "total": 0.0761011760000656, "count": 1, "self": 0.0010403510000287497, "children": { "RLTrainer._checkpoint": { "total": 0.07506082500003686, "count": 1, "self": 0.07506082500003686 } } } } } } }