{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.738983690738678, "min": 0.49195733666419983, "max": 1.3118427991867065, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 22145.86328125, "min": 14947.6318359375, "max": 39796.0625, "count": 16 }, "Pyramids.Step.mean": { "value": 479908.0, "min": 29903.0, "max": 479908.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479908.0, "min": 29903.0, "max": 479908.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03713126853108406, "min": -0.10277976840734482, "max": 0.03713126853108406, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 9.097160339355469, "min": -24.872703552246094, "max": 9.097160339355469, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04024461656808853, "min": 0.0300200954079628, "max": 0.5797380805015564, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.859930992126465, "min": 7.354923248291016, "max": 137.39791870117188, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06864996377992737, "min": 0.06540100464085023, "max": 0.07365103193059065, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9610994929189831, "min": 0.5155572235141346, "max": 0.9988405941670127, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005410192468505057, "min": 0.0009231757796349264, "max": 0.013681946543527728, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0757426945590708, "min": 0.010522280838797885, "max": 0.0957736258046941, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1345735741928573e-05, "min": 2.1345735741928573e-05, "max": 0.0002904700317480857, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029884030038700003, "min": 0.00029884030038700003, "max": 0.0028536009487998, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10711521428571429, "min": 0.10711521428571429, "max": 0.19682334285714287, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.499613, "min": 1.3777634, "max": 2.3396082000000002, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007208099071428573, "min": 0.0007208099071428573, "max": 0.009682651951428572, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.010091338700000002, "min": 0.010091338700000002, "max": 0.09515489998, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.027235398069024086, "min": 0.027235398069024086, "max": 0.5587548017501831, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3812955617904663, "min": 0.3812955617904663, "max": 3.9112837314605713, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 851.5833333333334, "min": 851.4117647058823, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30657.0, "min": 16702.0, "max": 32277.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.12967226654291153, "min": -0.999962551984936, "max": -0.12967226654291153, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -4.668201595544815, "min": -31.998801663517952, "max": -4.668201595544815, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.12967226654291153, "min": -0.999962551984936, "max": -0.12967226654291153, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -4.668201595544815, "min": -31.998801663517952, "max": -4.668201595544815, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.23885506172923165, "min": 0.23885506172923165, "max": 11.404472938355278, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 8.59878222225234, "min": 8.241848946548998, "max": 193.87603995203972, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679489615", "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": "1679490564" }, "total": 949.5795500689997, "count": 1, "self": 0.476823033999608, "children": { "run_training.setup": { "total": 0.11458128899994335, "count": 1, "self": 0.11458128899994335 }, "TrainerController.start_learning": { "total": 948.9881457460001, "count": 1, "self": 0.6016137709725626, "children": { "TrainerController._reset_env": { "total": 7.070178240000132, "count": 1, "self": 7.070178240000132 }, "TrainerController.advance": { "total": 941.2240850960275, "count": 31620, "self": 0.6592998469609483, "children": { "env_step": { "total": 637.2980345040755, "count": 31620, "self": 586.0284019521023, "children": { "SubprocessEnvManager._take_step": { "total": 50.89524606097439, "count": 31620, "self": 2.2538464990061584, "children": { "TorchPolicy.evaluate": { "total": 48.64139956196823, "count": 31317, "self": 48.64139956196823 } } }, "workers": { "total": 0.3743864909988588, "count": 31620, "self": 0.0, "children": { "worker_root": { "total": 947.0046194860397, "count": 31620, "is_parallel": true, "self": 414.42788671301423, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017473559996687982, "count": 1, "is_parallel": true, "self": 0.0005700420001630846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011773139995057136, "count": 8, "is_parallel": true, "self": 0.0011773139995057136 } } }, "UnityEnvironment.step": { "total": 0.04748465100010435, "count": 1, "is_parallel": true, "self": 0.0005115090002618672, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004314859997975873, "count": 1, "is_parallel": true, "self": 0.0004314859997975873 }, "communicator.exchange": { "total": 0.044885274000080244, "count": 1, "is_parallel": true, "self": 0.044885274000080244 }, "steps_from_proto": { "total": 0.0016563819999646512, "count": 1, "is_parallel": true, "self": 0.00037083900042489404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012855429995397571, "count": 8, "is_parallel": true, "self": 0.0012855429995397571 } } } } } } }, "UnityEnvironment.step": { "total": 532.5767327730255, "count": 31619, "is_parallel": true, "self": 15.02941522491301, "children": { "UnityEnvironment._generate_step_input": { "total": 11.005025104008382, "count": 31619, "is_parallel": true, "self": 11.005025104008382 }, "communicator.exchange": { "total": 462.5483772040575, "count": 31619, "is_parallel": true, "self": 462.5483772040575 }, "steps_from_proto": { "total": 43.99391524004659, "count": 31619, "is_parallel": true, "self": 9.238356631018178, "children": { "_process_rank_one_or_two_observation": { "total": 34.75555860902841, "count": 252952, "is_parallel": true, "self": 34.75555860902841 } } } } } } } } } } }, "trainer_advance": { "total": 303.266750744991, "count": 31620, "self": 1.1163099479704215, "children": { "process_trajectory": { "total": 55.47470573201781, "count": 31620, "self": 55.33351731701805, "children": { "RLTrainer._checkpoint": { "total": 0.14118841499976043, "count": 1, "self": 0.14118841499976043 } } }, "_update_policy": { "total": 246.67573506500275, "count": 217, "self": 156.72970990401336, "children": { "TorchPPOOptimizer.update": { "total": 89.9460251609894, "count": 11418, "self": 89.9460251609894 } } } } } } }, "trainer_threads": { "total": 1.018000148178544e-06, "count": 1, "self": 1.018000148178544e-06 }, "TrainerController._save_models": { "total": 0.09226762099979169, "count": 1, "self": 0.0014073519996600226, "children": { "RLTrainer._checkpoint": { "total": 0.09086026900013167, "count": 1, "self": 0.09086026900013167 } } } } } } }