{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37727248668670654, "min": 0.37727248668670654, "max": 1.4081470966339111, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11306.1015625, "min": 11306.1015625, "max": 42717.55078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1712152510881424, "min": -0.13355956971645355, "max": 0.20164908468723297, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 42.97502899169922, "min": -31.65361785888672, "max": 50.81557083129883, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 3.214146375656128, "min": -0.05830630660057068, "max": 3.214146375656128, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 806.750732421875, "min": -14.751495361328125, "max": 806.750732421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07358355896158733, "min": 0.06379145801872341, "max": 0.07412757877679466, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0301698254622227, "min": 0.5150370001080365, "max": 1.0535189734073356, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 1.642423048906331, "min": 0.00018046074396907815, "max": 1.7891540830180113, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 22.993922684688634, "min": 0.0018046074396907814, "max": 25.048157162252156, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.442176090735715e-06, "min": 7.442176090735715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001041904652703, "min": 0.0001041904652703, "max": 0.0031375031541657004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248069285714287, "min": 0.10248069285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347297, "min": 1.3691136000000002, "max": 2.4018587, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002578212164285714, "min": 0.0002578212164285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003609497029999999, "min": 0.003609497029999999, "max": 0.10460884657000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011353975161910057, "min": 0.011353975161910057, "max": 0.5443819761276245, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1589556485414505, "min": 0.1589556485414505, "max": 3.810673713684082, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 679.8333333333334, "min": 634.6888888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28553.0, "min": 15984.0, "max": 32293.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7009428202041558, "min": -1.0000000521540642, "max": 0.8755499666387384, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 29.439598448574543, "min": -32.000001668930054, "max": 38.52419853210449, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7009428202041558, "min": -1.0000000521540642, "max": 0.8755499666387384, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 29.439598448574543, "min": -32.000001668930054, "max": 38.52419853210449, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08355700146473412, "min": 0.08211637626333289, "max": 10.512702021747828, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.509394061518833, "min": 3.509394061518833, "max": 168.20323234796524, "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": "1721570599", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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 new --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721572687" }, "total": 2087.711869522, "count": 1, "self": 0.43151516900024944, "children": { "run_training.setup": { "total": 0.05110313899990615, "count": 1, "self": 0.05110313899990615 }, "TrainerController.start_learning": { "total": 2087.229251214, "count": 1, "self": 1.3144161739955962, "children": { "TrainerController._reset_env": { "total": 2.0221570520000114, "count": 1, "self": 2.0221570520000114 }, "TrainerController.advance": { "total": 2083.7973255870043, "count": 63311, "self": 1.35908006203681, "children": { "env_step": { "total": 1456.4823711999848, "count": 63311, "self": 1324.8675786290048, "children": { "SubprocessEnvManager._take_step": { "total": 130.8213776899563, "count": 63311, "self": 4.579287014976671, "children": { "TorchPolicy.evaluate": { "total": 126.24209067497964, "count": 62573, "self": 126.24209067497964 } } }, "workers": { "total": 0.7934148810236366, "count": 63311, "self": 0.0, "children": { "worker_root": { "total": 2082.336612929033, "count": 63311, "is_parallel": true, "self": 875.3649391350214, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020091609999326465, "count": 1, "is_parallel": true, "self": 0.0006392439997853216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013699170001473249, "count": 8, "is_parallel": true, "self": 0.0013699170001473249 } } }, "UnityEnvironment.step": { "total": 0.04749763600011647, "count": 1, "is_parallel": true, "self": 0.0006131930001629371, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042883299988716317, "count": 1, "is_parallel": true, "self": 0.00042883299988716317 }, "communicator.exchange": { "total": 0.04473236600006203, "count": 1, "is_parallel": true, "self": 0.04473236600006203 }, "steps_from_proto": { "total": 0.0017232440000043425, "count": 1, "is_parallel": true, "self": 0.00034434700023666664, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013788969997676759, "count": 8, "is_parallel": true, "self": 0.0013788969997676759 } } } } } } }, "UnityEnvironment.step": { "total": 1206.9716737940116, "count": 63310, "is_parallel": true, "self": 33.51971234104735, "children": { "UnityEnvironment._generate_step_input": { "total": 23.253507988016054, "count": 63310, "is_parallel": true, "self": 23.253507988016054 }, "communicator.exchange": { "total": 1053.419408567966, "count": 63310, "is_parallel": true, "self": 1053.419408567966 }, "steps_from_proto": { "total": 96.77904489698221, "count": 63310, "is_parallel": true, "self": 19.72930240486221, "children": { "_process_rank_one_or_two_observation": { "total": 77.04974249212, "count": 506480, "is_parallel": true, "self": 77.04974249212 } } } } } } } } } } }, "trainer_advance": { "total": 625.9558743249827, "count": 63311, "self": 2.5266871350108886, "children": { "process_trajectory": { "total": 124.40862699297281, "count": 63311, "self": 124.21299018297282, "children": { "RLTrainer._checkpoint": { "total": 0.19563680999999633, "count": 2, "self": 0.19563680999999633 } } }, "_update_policy": { "total": 499.020560196999, "count": 432, "self": 295.7687808930407, "children": { "TorchPPOOptimizer.update": { "total": 203.2517793039583, "count": 22926, "self": 203.2517793039583 } } } } } } }, "trainer_threads": { "total": 1.032999989547534e-06, "count": 1, "self": 1.032999989547534e-06 }, "TrainerController._save_models": { "total": 0.09535136800013788, "count": 1, "self": 0.0014560750000782718, "children": { "RLTrainer._checkpoint": { "total": 0.09389529300005961, "count": 1, "self": 0.09389529300005961 } } } } } } }