{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2992294430732727, "min": 0.2992294430732727, "max": 1.492452621459961, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9048.6982421875, "min": 9048.6982421875, "max": 45275.04296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29957.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29957.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.587913990020752, "min": -0.09508303552865982, "max": 0.6669148206710815, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.26426696777344, "min": -22.91501235961914, "max": 194.07220458984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011886782944202423, "min": -0.031833529472351074, "max": 0.20138977468013763, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.280752182006836, "min": -7.576379776000977, "max": 48.736324310302734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0704758680319459, "min": 0.06429999697040727, "max": 0.07241002595678549, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9866621524472425, "min": 0.5020450306949259, "max": 1.0506646613745638, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014914674551175816, "min": 0.0001606622993645703, "max": 0.015761754097286067, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20880544371646143, "min": 0.0022492721911039843, "max": 0.2339067940566547, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.690511722242855e-06, "min": 7.690511722242855e-06, "max": 0.00029523818730155715, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010766716411139996, "min": 0.00010766716411139996, "max": 0.0036084981971673, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256347142857143, "min": 0.10256347142857143, "max": 0.19841272857142855, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358886, "min": 1.3888890999999999, "max": 2.5695068, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026609079571428566, "min": 0.00026609079571428566, "max": 0.009841431584285715, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037252711399999995, "min": 0.0037252711399999995, "max": 0.12029298673, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01237169187515974, "min": 0.01237169187515974, "max": 0.3624524772167206, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17320369184017181, "min": 0.17320369184017181, "max": 2.5371673107147217, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.22727272727275, "min": 284.6990291262136, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28884.0, "min": 16628.0, "max": 32781.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.649034072306346, "min": -0.9998375521972775, "max": 1.7141851693115853, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.11499836295843, "min": -31.99480167031288, "max": 185.1319982856512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.649034072306346, "min": -0.9998375521972775, "max": 1.7141851693115853, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.11499836295843, "min": -31.99480167031288, "max": 185.1319982856512, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04222177033476659, "min": 0.03835009137839328, "max": 7.25148319453001, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7155157894594595, "min": 3.7155157894594595, "max": 123.27521430701017, "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": "1679200891", "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": "1679203020" }, "total": 2129.645745955, "count": 1, "self": 0.4741174550008509, "children": { "run_training.setup": { "total": 0.10579601399967942, "count": 1, "self": 0.10579601399967942 }, "TrainerController.start_learning": { "total": 2129.0658324859996, "count": 1, "self": 1.506976754923926, "children": { "TrainerController._reset_env": { "total": 6.197753757999635, "count": 1, "self": 6.197753757999635 }, "TrainerController.advance": { "total": 2121.268153165076, "count": 64017, "self": 1.602584594106247, "children": { "env_step": { "total": 1503.9630158600344, "count": 64017, "self": 1389.157125215048, "children": { "SubprocessEnvManager._take_step": { "total": 113.89014844903159, "count": 64017, "self": 4.751692930037734, "children": { "TorchPolicy.evaluate": { "total": 109.13845551899385, "count": 62558, "self": 109.13845551899385 } } }, "workers": { "total": 0.9157421959548628, "count": 64017, "self": 0.0, "children": { "worker_root": { "total": 2124.198507129002, "count": 64017, "is_parallel": true, "self": 853.9254579731282, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019010460000572493, "count": 1, "is_parallel": true, "self": 0.0006330769997475727, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012679690003096766, "count": 8, "is_parallel": true, "self": 0.0012679690003096766 } } }, "UnityEnvironment.step": { "total": 0.08576096200022221, "count": 1, "is_parallel": true, "self": 0.0005926660001023265, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040959699981613085, "count": 1, "is_parallel": true, "self": 0.00040959699981613085 }, "communicator.exchange": { "total": 0.08316502000025139, "count": 1, "is_parallel": true, "self": 0.08316502000025139 }, "steps_from_proto": { "total": 0.0015936790000523615, "count": 1, "is_parallel": true, "self": 0.00036088500019104686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012327939998613147, "count": 8, "is_parallel": true, "self": 0.0012327939998613147 } } } } } } }, "UnityEnvironment.step": { "total": 1270.2730491558737, "count": 64016, "is_parallel": true, "self": 31.001365252864616, "children": { "UnityEnvironment._generate_step_input": { "total": 22.399567527079853, "count": 64016, "is_parallel": true, "self": 22.399567527079853 }, "communicator.exchange": { "total": 1125.852470723948, "count": 64016, "is_parallel": true, "self": 1125.852470723948 }, "steps_from_proto": { "total": 91.01964565198114, "count": 64016, "is_parallel": true, "self": 19.654464270681274, "children": { "_process_rank_one_or_two_observation": { "total": 71.36518138129986, "count": 512128, "is_parallel": true, "self": 71.36518138129986 } } } } } } } } } } }, "trainer_advance": { "total": 615.7025527109354, "count": 64017, "self": 2.8630582349819633, "children": { "process_trajectory": { "total": 117.09458153496371, "count": 64017, "self": 116.89556704396409, "children": { "RLTrainer._checkpoint": { "total": 0.1990144909996161, "count": 2, "self": 0.1990144909996161 } } }, "_update_policy": { "total": 495.7449129409897, "count": 458, "self": 312.1669926319523, "children": { "TorchPPOOptimizer.update": { "total": 183.57792030903738, "count": 22791, "self": 183.57792030903738 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.09294786600003135, "count": 1, "self": 0.0014057910002520657, "children": { "RLTrainer._checkpoint": { "total": 0.09154207499977929, "count": 1, "self": 0.09154207499977929 } } } } } } }