{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9872178435325623, "min": 0.9872178435325623, "max": 2.864316463470459, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9447.6748046875, "min": 9447.6748046875, "max": 29427.98828125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.12951946258545, "min": 0.49277621507644653, "max": 13.12951946258545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2560.25634765625, "min": 95.59858703613281, "max": 2669.49609375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07206193343211222, "min": 0.062253106212652065, "max": 0.07718792081081224, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28824773372844886, "min": 0.24901242485060826, "max": 0.38593960405406125, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19436689385888622, "min": 0.14922309038914083, "max": 0.2859529435050254, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7774675754355449, "min": 0.5968923615565633, "max": 1.4297647175251271, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.429097306000008e-06, "min": 9.429097306000008e-06, "max": 0.0003405290027059999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.771638922400003e-05, "min": 3.771638922400003e-05, "max": 0.00161602003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.068181818181817, "min": 4.0227272727272725, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 177.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 4.0227272727272725, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 177.0, "max": 1424.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691853028", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1691853521" }, "total": 492.39752079699997, "count": 1, "self": 0.8058973659999538, "children": { "run_training.setup": { "total": 0.04267904699997871, "count": 1, "self": 0.04267904699997871 }, "TrainerController.start_learning": { "total": 491.54894438400004, "count": 1, "self": 0.557145191010818, "children": { "TrainerController._reset_env": { "total": 4.26308811399997, "count": 1, "self": 4.26308811399997 }, "TrainerController.advance": { "total": 486.4905491589892, "count": 18214, "self": 0.2833127629767205, "children": { "env_step": { "total": 486.2072363960125, "count": 18214, "self": 354.1492947799767, "children": { "SubprocessEnvManager._take_step": { "total": 131.76670779102471, "count": 18214, "self": 1.8915502300277467, "children": { "TorchPolicy.evaluate": { "total": 129.87515756099697, "count": 18214, "self": 129.87515756099697 } } }, "workers": { "total": 0.29123382501109063, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 489.80162410300886, "count": 18214, "is_parallel": true, "self": 232.03202809399534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006038450000005469, "count": 1, "is_parallel": true, "self": 0.0045601340000303026, "children": { "_process_rank_one_or_two_observation": { "total": 0.001478315999975166, "count": 10, "is_parallel": true, "self": 0.001478315999975166 } } }, "UnityEnvironment.step": { "total": 0.039450494999982766, "count": 1, "is_parallel": true, "self": 0.0007195629999614539, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034687499999108695, "count": 1, "is_parallel": true, "self": 0.00034687499999108695 }, "communicator.exchange": { "total": 0.03617259899999681, "count": 1, "is_parallel": true, "self": 0.03617259899999681 }, "steps_from_proto": { "total": 0.002211458000033417, "count": 1, "is_parallel": true, "self": 0.00039111000000957574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018203480000238415, "count": 10, "is_parallel": true, "self": 0.0018203480000238415 } } } } } } }, "UnityEnvironment.step": { "total": 257.7695960090135, "count": 18213, "is_parallel": true, "self": 11.04661722101207, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6768374609990815, "count": 18213, "is_parallel": true, "self": 5.6768374609990815 }, "communicator.exchange": { "total": 203.44631532900485, "count": 18213, "is_parallel": true, "self": 203.44631532900485 }, "steps_from_proto": { "total": 37.59982599799753, "count": 18213, "is_parallel": true, "self": 6.967339698023579, "children": { "_process_rank_one_or_two_observation": { "total": 30.632486299973948, "count": 182130, "is_parallel": true, "self": 30.632486299973948 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001729949999571545, "count": 1, "self": 0.0001729949999571545, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.8354018140391, "count": 447608, "is_parallel": true, "self": 10.027455348114472, "children": { "process_trajectory": { "total": 264.4766707779247, "count": 447608, "is_parallel": true, "self": 263.3299029989248, "children": { "RLTrainer._checkpoint": { "total": 1.1467677789999016, "count": 4, "is_parallel": true, "self": 1.1467677789999016 } } }, "_update_policy": { "total": 208.3312756879999, "count": 90, "is_parallel": true, "self": 82.15911936700093, "children": { "TorchPPOOptimizer.update": { "total": 126.17215632099897, "count": 4587, "is_parallel": true, "self": 126.17215632099897 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2379889250000815, "count": 1, "self": 0.001198662000206241, "children": { "RLTrainer._checkpoint": { "total": 0.23679026299987527, "count": 1, "self": 0.23679026299987527 } } } } } } }