{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.463517963886261, "min": 0.4533245265483856, "max": 1.459008812904358, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13964.869140625, "min": 13482.865234375, "max": 44260.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29913.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29913.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4789871871471405, "min": -0.10047843307256699, "max": 0.5532966256141663, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.28451538085938, "min": -24.315780639648438, "max": 154.3697509765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009280841797590256, "min": 0.00644303672015667, "max": 0.23838819563388824, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5243890285491943, "min": 1.5592148303985596, "max": 56.49800109863281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0673857955701856, "min": 0.06413194288205935, "max": 0.07273836340700267, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0107869335527842, "min": 0.5091685438490187, "max": 1.0324496912082894, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01604025702884731, "min": 0.0007724836082668743, "max": 0.01743947066063324, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24060385543270965, "min": 0.01081477051573624, "max": 0.24564770540746392, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4426975191333305e-06, "min": 7.4426975191333305e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011164046278699996, "min": 0.00011164046278699996, "max": 0.0037581388472870997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248086666666666, "min": 0.10248086666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537213, "min": 1.3886848, "max": 2.6527129, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025783857999999994, "min": 0.00025783857999999994, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038675786999999994, "min": 0.0038675786999999994, "max": 0.12528601871000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009184201247990131, "min": 0.009184201247990131, "max": 0.3884141743183136, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13776302337646484, "min": 0.1351100504398346, "max": 2.7188992500305176, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 387.5844155844156, "min": 321.4782608695652, "max": 997.6333333333333, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29844.0, "min": 16840.0, "max": 33254.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5344805014984948, "min": -0.9316867190102737, "max": 1.6132825920763223, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.1549986153841, "min": -28.218201704323292, "max": 148.42199847102165, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5344805014984948, "min": -0.9316867190102737, "max": 1.6132825920763223, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.1549986153841, "min": -28.218201704323292, "max": 148.42199847102165, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03672610307505427, "min": 0.03217995077226948, "max": 7.690991434104302, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8279099367791787, "min": 2.8279099367791787, "max": 130.74685437977314, "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": "1720023473", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720025766" }, "total": 2293.159648346, "count": 1, "self": 0.5809694609997678, "children": { "run_training.setup": { "total": 0.056248764999963896, "count": 1, "self": 0.056248764999963896 }, "TrainerController.start_learning": { "total": 2292.52243012, "count": 1, "self": 1.5291125939579615, "children": { "TrainerController._reset_env": { "total": 2.9597422669999105, "count": 1, "self": 2.9597422669999105 }, "TrainerController.advance": { "total": 2287.938183929042, "count": 63813, "self": 1.520901688061258, "children": { "env_step": { "total": 1607.1957797959828, "count": 63813, "self": 1467.2834005599707, "children": { "SubprocessEnvManager._take_step": { "total": 138.98623399403778, "count": 63813, "self": 4.918276974048695, "children": { "TorchPolicy.evaluate": { "total": 134.06795701998908, "count": 62545, "self": 134.06795701998908 } } }, "workers": { "total": 0.9261452419743819, "count": 63813, "self": 0.0, "children": { "worker_root": { "total": 2287.398150821039, "count": 63813, "is_parallel": true, "self": 950.1177328320766, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021041119998699287, "count": 1, "is_parallel": true, "self": 0.0006066869996175228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014974250002524059, "count": 8, "is_parallel": true, "self": 0.0014974250002524059 } } }, "UnityEnvironment.step": { "total": 0.10678609499996128, "count": 1, "is_parallel": true, "self": 0.0007274150000284862, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004757680001148401, "count": 1, "is_parallel": true, "self": 0.0004757680001148401 }, "communicator.exchange": { "total": 0.10391382099987823, "count": 1, "is_parallel": true, "self": 0.10391382099987823 }, "steps_from_proto": { "total": 0.0016690909999397263, "count": 1, "is_parallel": true, "self": 0.00034679999998843414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013222909999512922, "count": 8, "is_parallel": true, "self": 0.0013222909999512922 } } } } } } }, "UnityEnvironment.step": { "total": 1337.2804179889624, "count": 63812, "is_parallel": true, "self": 37.13434601986705, "children": { "UnityEnvironment._generate_step_input": { "total": 24.730874310005447, "count": 63812, "is_parallel": true, "self": 24.730874310005447 }, "communicator.exchange": { "total": 1172.2282801310153, "count": 63812, "is_parallel": true, "self": 1172.2282801310153 }, "steps_from_proto": { "total": 103.18691752807467, "count": 63812, "is_parallel": true, "self": 21.32063098181493, "children": { "_process_rank_one_or_two_observation": { "total": 81.86628654625974, "count": 510496, "is_parallel": true, "self": 81.86628654625974 } } } } } } } } } } }, "trainer_advance": { "total": 679.2215024449984, "count": 63813, "self": 2.915941159013528, "children": { "process_trajectory": { "total": 136.53364377698404, "count": 63813, "self": 136.33482087498373, "children": { "RLTrainer._checkpoint": { "total": 0.19882290200030184, "count": 2, "self": 0.19882290200030184 } } }, "_update_policy": { "total": 539.7719175090008, "count": 458, "self": 321.51204054895493, "children": { "TorchPPOOptimizer.update": { "total": 218.25987696004586, "count": 22761, "self": 218.25987696004586 } } } } } } }, "trainer_threads": { "total": 9.350001164420974e-07, "count": 1, "self": 9.350001164420974e-07 }, "TrainerController._save_models": { "total": 0.09539039499986757, "count": 1, "self": 0.002154580000023998, "children": { "RLTrainer._checkpoint": { "total": 0.09323581499984357, "count": 1, "self": 0.09323581499984357 } } } } } } }