{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9617084860801697, "min": 0.9606256484985352, "max": 2.8498311042785645, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9182.392578125, "min": 9182.392578125, "max": 29185.119140625, "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": 12.546526908874512, "min": 0.42490583658218384, "max": 12.546526908874512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2446.57275390625, "min": 82.43173217773438, "max": 2529.56298828125, "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": 0.06544848280028936, "min": 0.06342689899611287, "max": 0.07338656424282246, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26179393120115746, "min": 0.2537075959844515, "max": 0.3669328212141123, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.197339546227572, "min": 0.12319076693657896, "max": 0.2898862727716857, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.789358184910288, "min": 0.49276306774631584, "max": 1.4494313638584286, "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": 24.90909090909091, "min": 3.2954545454545454, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 145.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 3.2954545454545454, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 145.0, "max": 1356.0, "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": "1716926352", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716926792" }, "total": 440.75515400099994, "count": 1, "self": 0.42480993900016983, "children": { "run_training.setup": { "total": 0.050466502999825025, "count": 1, "self": 0.050466502999825025 }, "TrainerController.start_learning": { "total": 440.27987755899994, "count": 1, "self": 0.5417273469838619, "children": { "TrainerController._reset_env": { "total": 3.056555577999916, "count": 1, "self": 3.056555577999916 }, "TrainerController.advance": { "total": 436.5943016500164, "count": 18201, "self": 0.2684361140218243, "children": { "env_step": { "total": 436.3258655359946, "count": 18201, "self": 283.36747863100936, "children": { "SubprocessEnvManager._take_step": { "total": 152.6887854349584, "count": 18201, "self": 1.4402533999837033, "children": { "TorchPolicy.evaluate": { "total": 151.2485320349747, "count": 18201, "self": 151.2485320349747 } } }, "workers": { "total": 0.2696014700268279, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 439.06529793697564, "count": 18201, "is_parallel": true, "self": 221.48071745697825, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008614988999852358, "count": 1, "is_parallel": true, "self": 0.006973696999011736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016412920008406218, "count": 10, "is_parallel": true, "self": 0.0016412920008406218 } } }, "UnityEnvironment.step": { "total": 0.035571041999901354, "count": 1, "is_parallel": true, "self": 0.0006827529991824122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040830000034475233, "count": 1, "is_parallel": true, "self": 0.00040830000034475233 }, "communicator.exchange": { "total": 0.032634813000186114, "count": 1, "is_parallel": true, "self": 0.032634813000186114 }, "steps_from_proto": { "total": 0.0018451760001880757, "count": 1, "is_parallel": true, "self": 0.00034555100046418374, "children": { "_process_rank_one_or_two_observation": { "total": 0.001499624999723892, "count": 10, "is_parallel": true, "self": 0.001499624999723892 } } } } } } }, "UnityEnvironment.step": { "total": 217.58458047999738, "count": 18200, "is_parallel": true, "self": 9.979514889017992, "children": { "UnityEnvironment._generate_step_input": { "total": 5.164853657999629, "count": 18200, "is_parallel": true, "self": 5.164853657999629 }, "communicator.exchange": { "total": 170.2726533519858, "count": 18200, "is_parallel": true, "self": 170.2726533519858 }, "steps_from_proto": { "total": 32.167558580993955, "count": 18200, "is_parallel": true, "self": 6.058137713153428, "children": { "_process_rank_one_or_two_observation": { "total": 26.109420867840527, "count": 182000, "is_parallel": true, "self": 26.109420867840527 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012829900015276507, "count": 1, "self": 0.00012829900015276507, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.2760015052386, "count": 657917, "is_parallel": true, "self": 13.406860965124451, "children": { "process_trajectory": { "total": 241.18955001411314, "count": 657917, "is_parallel": true, "self": 240.52030590711274, "children": { "RLTrainer._checkpoint": { "total": 0.6692441070003952, "count": 4, "is_parallel": true, "self": 0.6692441070003952 } } }, "_update_policy": { "total": 176.679590526001, "count": 90, "is_parallel": true, "self": 55.418715355022414, "children": { "TorchPPOOptimizer.update": { "total": 121.26087517097858, "count": 4587, "is_parallel": true, "self": 121.26087517097858 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08716468499960683, "count": 1, "self": 0.0009079299998120405, "children": { "RLTrainer._checkpoint": { "total": 0.0862567549997948, "count": 1, "self": 0.0862567549997948 } } } } } } }