{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7151013612747192, "min": 0.7151013612747192, "max": 1.4768272638320923, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 21441.599609375, "min": 21441.599609375, "max": 44801.03125, "count": 3 }, "Pyramids.Step.mean": { "value": 89923.0, "min": 29930.0, "max": 89923.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89923.0, "min": 29930.0, "max": 89923.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08861732482910156, "min": -0.10084986686706543, "max": -0.03741351142525673, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.268157958984375, "min": -24.30481719970703, "max": -8.867002487182617, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2454124093055725, "min": 0.2454124093055725, "max": 0.5892899632453918, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 58.89897918701172, "min": 58.89897918701172, "max": 139.66172790527344, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06920775743001878, "min": 0.06920775743001878, "max": 0.07416160593694575, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8997008465902441, "min": 0.5191312415586202, "max": 0.8997008465902441, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0004564289065915861, "min": 0.0004564289065915861, "max": 0.01182457747683376, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.005933575785690619, "min": 0.005933575785690619, "max": 0.08277204233783632, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.593076699746153e-05, "min": 7.593076699746153e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000987099970967, "min": 0.000987099970967, "max": 0.0018297754900750002, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12531023076923076, "min": 0.12531023076923076, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.629033, "min": 1.2868480000000002, "max": 1.709925, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025384920538461535, "min": 0.0025384920538461535, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0330003967, "min": 0.0330003967, "max": 0.06104150750000001, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.1585404872894287, "min": 0.1585404872894287, "max": 0.6057981848716736, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.0610263347625732, "min": 2.0610263347625732, "max": 4.24058723449707, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 989.03125, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 16857.0, "max": 31649.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999226326903989, "min": -0.9999226326903989, "max": -0.8649188012350351, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.997601613402367, "min": -30.997601613402367, "max": -14.873000890016556, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999226326903989, "min": -0.9999226326903989, "max": -0.8649188012350351, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.997601613402367, "min": -30.997601613402367, "max": -14.873000890016556, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.860380296745608, "min": 1.860380296745608, "max": 11.506214489831644, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 57.671789199113846, "min": 57.671789199113846, "max": 195.60564632713795, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704447674", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704447878" }, "total": 204.19577062300004, "count": 1, "self": 0.47653033599999617, "children": { "run_training.setup": { "total": 0.045323929999995016, "count": 1, "self": 0.045323929999995016 }, "TrainerController.start_learning": { "total": 203.67391635700005, "count": 1, "self": 0.12931566799397842, "children": { "TrainerController._reset_env": { "total": 2.03130759700025, "count": 1, "self": 2.03130759700025 }, "TrainerController.advance": { "total": 201.4039722590055, "count": 6293, "self": 0.14034775600339344, "children": { "env_step": { "total": 137.6886233070113, "count": 6293, "self": 124.1414707509748, "children": { "SubprocessEnvManager._take_step": { "total": 13.464441286008423, "count": 6293, "self": 0.4770016550132823, "children": { "TorchPolicy.evaluate": { "total": 12.98743963099514, "count": 6278, "self": 12.98743963099514 } } }, "workers": { "total": 0.08271127002808498, "count": 6293, "self": 0.0, "children": { "worker_root": { "total": 203.07956620701134, "count": 6293, "is_parallel": true, "self": 91.3353706690018, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001778115999968577, "count": 1, "is_parallel": true, "self": 0.0005827370000588417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011953789999097353, "count": 8, "is_parallel": true, "self": 0.0011953789999097353 } } }, "UnityEnvironment.step": { "total": 0.05097948399998131, "count": 1, "is_parallel": true, "self": 0.0005680190001839946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004939699997521529, "count": 1, "is_parallel": true, "self": 0.0004939699997521529 }, "communicator.exchange": { "total": 0.048305165999863675, "count": 1, "is_parallel": true, "self": 0.048305165999863675 }, "steps_from_proto": { "total": 0.0016123290001814894, "count": 1, "is_parallel": true, "self": 0.00034772300023178104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012646059999497083, "count": 8, "is_parallel": true, "self": 0.0012646059999497083 } } } } } } }, "UnityEnvironment.step": { "total": 111.74419553800954, "count": 6292, "is_parallel": true, "self": 3.515597676053403, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7053540349907053, "count": 6292, "is_parallel": true, "self": 2.7053540349907053 }, "communicator.exchange": { "total": 95.20404506799696, "count": 6292, "is_parallel": true, "self": 95.20404506799696 }, "steps_from_proto": { "total": 10.319198758968469, "count": 6292, "is_parallel": true, "self": 2.0688690879896967, "children": { "_process_rank_one_or_two_observation": { "total": 8.250329670978772, "count": 50336, "is_parallel": true, "self": 8.250329670978772 } } } } } } } } } } }, "trainer_advance": { "total": 63.57500119599081, "count": 6293, "self": 0.18322160399384302, "children": { "process_trajectory": { "total": 12.284347761996742, "count": 6293, "self": 12.284347761996742 }, "_update_policy": { "total": 51.10743183000022, "count": 35, "self": 29.932208054012335, "children": { "TorchPPOOptimizer.update": { "total": 21.175223775987888, "count": 2319, "self": 21.175223775987888 } } } } } } }, "trainer_threads": { "total": 1.100000190490391e-06, "count": 1, "self": 1.100000190490391e-06 }, "TrainerController._save_models": { "total": 0.10931973300012032, "count": 1, "self": 0.001582632999998168, "children": { "RLTrainer._checkpoint": { "total": 0.10773710000012215, "count": 1, "self": 0.10773710000012215 } } } } } } }