{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9298079609870911, "min": 0.9298079609870911, "max": 2.865370273590088, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8888.0341796875, "min": 8888.0341796875, "max": 29344.255859375, "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": 24.89508628845215, "min": 0.4889114201068878, "max": 24.89508628845215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4854.5419921875, "min": 94.84881591796875, "max": 5012.6328125, "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": 0.1013740585074308, "min": 0.09212024473566928, "max": 0.10579802049818521, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.4054962340297232, "min": 0.36973842653721617, "max": 0.528990102490926, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21694867298299192, "min": 0.12499124424524308, "max": 0.29776500004763695, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8677946919319677, "min": 0.4999649769809723, "max": 1.473128924913266, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.295454545454547, "min": 3.590909090909091, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 158.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.590909090909091, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 158.0, "max": 1392.0, "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": "1675781104", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675781598" }, "total": 493.786089862, "count": 1, "self": 0.38727642200001355, "children": { "run_training.setup": { "total": 0.11687641899999335, "count": 1, "self": 0.11687641899999335 }, "TrainerController.start_learning": { "total": 493.281937021, "count": 1, "self": 0.5216737689962088, "children": { "TrainerController._reset_env": { "total": 9.941745424999965, "count": 1, "self": 9.941745424999965 }, "TrainerController.advance": { "total": 482.70020132600393, "count": 18203, "self": 0.27479938701105766, "children": { "env_step": { "total": 482.4254019389929, "count": 18203, "self": 354.7982986659954, "children": { "SubprocessEnvManager._take_step": { "total": 127.3618536799994, "count": 18203, "self": 1.4495117819991492, "children": { "TorchPolicy.evaluate": { "total": 125.91234189800025, "count": 18203, "self": 28.368747949009844, "children": { "TorchPolicy.sample_actions": { "total": 97.5435939489904, "count": 18203, "self": 97.5435939489904 } } } } }, "workers": { "total": 0.2652495929980887, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 491.82898301701056, "count": 18203, "is_parallel": true, "self": 256.45849313601644, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007157586000005267, "count": 1, "is_parallel": true, "self": 0.003983935000007932, "children": { "_process_rank_one_or_two_observation": { "total": 0.003173650999997335, "count": 10, "is_parallel": true, "self": 0.003173650999997335 } } }, "UnityEnvironment.step": { "total": 0.03546200099992802, "count": 1, "is_parallel": true, "self": 0.0005217080000647911, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037661800001842494, "count": 1, "is_parallel": true, "self": 0.00037661800001842494 }, "communicator.exchange": { "total": 0.03274746399995365, "count": 1, "is_parallel": true, "self": 0.03274746399995365 }, "steps_from_proto": { "total": 0.0018162109998911546, "count": 1, "is_parallel": true, "self": 0.0004163659998539515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013998450000372031, "count": 10, "is_parallel": true, "self": 0.0013998450000372031 } } } } } } }, "UnityEnvironment.step": { "total": 235.3704898809941, "count": 18202, "is_parallel": true, "self": 9.33802555100874, "children": { "UnityEnvironment._generate_step_input": { "total": 5.161479531995383, "count": 18202, "is_parallel": true, "self": 5.161479531995383 }, "communicator.exchange": { "total": 187.60701614198706, "count": 18202, "is_parallel": true, "self": 187.60701614198706 }, "steps_from_proto": { "total": 33.26396865600293, "count": 18202, "is_parallel": true, "self": 6.823795070038273, "children": { "_process_rank_one_or_two_observation": { "total": 26.440173585964658, "count": 182020, "is_parallel": true, "self": 26.440173585964658 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001682149999169269, "count": 1, "self": 0.0001682149999169269, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.50389971199775, "count": 393741, "is_parallel": true, "self": 9.585560421987793, "children": { "process_trajectory": { "total": 251.68990381801052, "count": 393741, "is_parallel": true, "self": 250.88943840301056, "children": { "RLTrainer._checkpoint": { "total": 0.8004654149999624, "count": 4, "is_parallel": true, "self": 0.8004654149999624 } } }, "_update_policy": { "total": 218.22843547199943, "count": 90, "is_parallel": true, "self": 60.069739126994136, "children": { "TorchPPOOptimizer.update": { "total": 158.1586963450053, "count": 9177, "is_parallel": true, "self": 158.1586963450053 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11814828599995053, "count": 1, "self": 0.000845062999928814, "children": { "RLTrainer._checkpoint": { "total": 0.11730322300002172, "count": 1, "self": 0.11730322300002172 } } } } } } }