{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1683014631271362, "min": 1.1683014631271362, "max": 2.859931468963623, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11206.34765625, "min": 11206.34765625, "max": 29445.853515625, "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": 12.014347076416016, "min": 0.3163045644760132, "max": 12.014347076416016, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2342.797607421875, "min": 61.36308670043945, "max": 2386.34619140625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06841762584286593, "min": 0.06275709605200545, "max": 0.07535542392974558, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2736705033714637, "min": 0.25682676194849713, "max": 0.36090321970279515, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2148721256092483, "min": 0.101295092267523, "max": 0.29770819419154937, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8594885024369932, "min": 0.405180369070092, "max": 1.404177508225628, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "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": 25.0, "min": 2.909090909090909, "max": 25.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 128.0, "max": 1253.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 2.909090909090909, "max": 25.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 128.0, "max": 1253.0, "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": "1700764355", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/home/ftorresa/.pyenv/versions/3.9.18-huggingface-deeprl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1700764612" }, "total": 257.196180844001, "count": 1, "self": 0.2684102350012836, "children": { "run_training.setup": { "total": 0.019739751998713473, "count": 1, "self": 0.019739751998713473 }, "TrainerController.start_learning": { "total": 256.908030857001, "count": 1, "self": 0.24953880295652198, "children": { "TrainerController._reset_env": { "total": 0.6027415959997597, "count": 1, "self": 0.6027415959997597 }, "TrainerController.advance": { "total": 256.00682555804633, "count": 18204, "self": 0.11287395800900413, "children": { "env_step": { "total": 255.89395160003733, "count": 18204, "self": 212.75451469711334, "children": { "SubprocessEnvManager._take_step": { "total": 43.01071394090468, "count": 18204, "self": 0.6006196478792845, "children": { "TorchPolicy.evaluate": { "total": 42.410094293025395, "count": 18204, "self": 42.410094293025395 } } }, "workers": { "total": 0.12872296201931022, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 256.5081219661006, "count": 18204, "is_parallel": true, "self": 101.7276187199077, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001937798999279039, "count": 1, "is_parallel": true, "self": 0.0004738349980470957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014639640012319433, "count": 10, "is_parallel": true, "self": 0.0014639640012319433 } } }, "UnityEnvironment.step": { "total": 0.017547471999932895, "count": 1, "is_parallel": true, "self": 0.0004944520005665254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003175609999743756, "count": 1, "is_parallel": true, "self": 0.0003175609999743756 }, "communicator.exchange": { "total": 0.01541806400018686, "count": 1, "is_parallel": true, "self": 0.01541806400018686 }, "steps_from_proto": { "total": 0.0013173949992051348, "count": 1, "is_parallel": true, "self": 0.000244147999183042, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010732470000220928, "count": 10, "is_parallel": true, "self": 0.0010732470000220928 } } } } } } }, "UnityEnvironment.step": { "total": 154.7805032461929, "count": 18203, "is_parallel": true, "self": 7.699148369323666, "children": { "UnityEnvironment._generate_step_input": { "total": 3.6535450378905807, "count": 18203, "is_parallel": true, "self": 3.6535450378905807 }, "communicator.exchange": { "total": 123.13561485397622, "count": 18203, "is_parallel": true, "self": 123.13561485397622 }, "steps_from_proto": { "total": 20.292194985002425, "count": 18203, "is_parallel": true, "self": 3.3448654904495925, "children": { "_process_rank_one_or_two_observation": { "total": 16.947329494552832, "count": 182030, "is_parallel": true, "self": 16.947329494552832 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00024016299903451, "count": 1, "self": 0.00024016299903451, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 255.0721189558226, "count": 228773, "is_parallel": true, "self": 2.8279931161250715, "children": { "process_trajectory": { "total": 144.28028202968198, "count": 228773, "is_parallel": true, "self": 143.95537726868133, "children": { "RLTrainer._checkpoint": { "total": 0.3249047610006528, "count": 4, "is_parallel": true, "self": 0.3249047610006528 } } }, "_update_policy": { "total": 107.96384381001553, "count": 90, "is_parallel": true, "self": 25.18933175310849, "children": { "TorchPPOOptimizer.update": { "total": 82.77451205690704, "count": 4587, "is_parallel": true, "self": 82.77451205690704 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04868473699934839, "count": 1, "self": 0.0004689939996751491, "children": { "RLTrainer._checkpoint": { "total": 0.04821574299967324, "count": 1, "self": 0.04821574299967324 } } } } } } }