{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.4930074214935303, "min": 1.4930074214935303, "max": 2.8658833503723145, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15322.7353515625, "min": 15130.439453125, "max": 29349.51171875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.843406677246094, "min": 0.35325509309768677, "max": 8.843406677246094, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1804.0550537109375, "min": 68.53148651123047, "max": 1804.0550537109375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06663167460398708, "min": 0.06318576157349276, "max": 0.07259438056679951, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3331583730199354, "min": 0.2543781210905781, "max": 0.34657238281044345, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2752010445384418, "min": 0.1200975201437341, "max": 0.3076283942688914, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.376005222692209, "min": 0.4803900805749364, "max": 1.3895390220716888, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.072727272727274, "min": 3.4318181818181817, "max": 19.072727272727274, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1049.0, "min": 151.0, "max": 1049.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.072727272727274, "min": 3.4318181818181817, "max": 19.072727272727274, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1049.0, "min": 151.0, "max": 1049.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674467422", "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": "1674467657" }, "total": 234.25082756099994, "count": 1, "self": 0.3865640359998679, "children": { "run_training.setup": { "total": 0.11032887300001448, "count": 1, "self": 0.11032887300001448 }, "TrainerController.start_learning": { "total": 233.75393465200005, "count": 1, "self": 0.30606029999950124, "children": { "TrainerController._reset_env": { "total": 9.058995783, "count": 1, "self": 9.058995783 }, "TrainerController.advance": { "total": 224.26249934400062, "count": 9136, "self": 0.1445515229942771, "children": { "env_step": { "total": 224.11794782100634, "count": 9136, "self": 145.90762491100008, "children": { "SubprocessEnvManager._take_step": { "total": 78.06601162500039, "count": 9136, "self": 0.7461370690028843, "children": { "TorchPolicy.evaluate": { "total": 77.3198745559975, "count": 9136, "self": 16.841938163003192, "children": { "TorchPolicy.sample_actions": { "total": 60.47793639299431, "count": 9136, "self": 60.47793639299431 } } } } }, "workers": { "total": 0.14431128500586965, "count": 9136, "self": 0.0, "children": { "worker_root": { "total": 233.10224092600424, "count": 9136, "is_parallel": true, "self": 113.65988475000762, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006908672000008664, "count": 1, "is_parallel": true, "self": 0.0036875999999210762, "children": { "_process_rank_one_or_two_observation": { "total": 0.003221072000087588, "count": 10, "is_parallel": true, "self": 0.003221072000087588 } } }, "UnityEnvironment.step": { "total": 0.036134608999986995, "count": 1, "is_parallel": true, "self": 0.0005822489999331992, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031795800003919794, "count": 1, "is_parallel": true, "self": 0.00031795800003919794 }, "communicator.exchange": { "total": 0.033226103999993484, "count": 1, "is_parallel": true, "self": 0.033226103999993484 }, "steps_from_proto": { "total": 0.0020082980000211137, "count": 1, "is_parallel": true, "self": 0.0004280240000298363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015802739999912774, "count": 10, "is_parallel": true, "self": 0.0015802739999912774 } } } } } } }, "UnityEnvironment.step": { "total": 119.44235617599662, "count": 9135, "is_parallel": true, "self": 4.44595483299679, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7179904039972484, "count": 9135, "is_parallel": true, "self": 2.7179904039972484 }, "communicator.exchange": { "total": 94.40597234999785, "count": 9135, "is_parallel": true, "self": 94.40597234999785 }, "steps_from_proto": { "total": 17.87243858900473, "count": 9135, "is_parallel": true, "self": 3.617159960001402, "children": { "_process_rank_one_or_two_observation": { "total": 14.255278629003328, "count": 91350, "is_parallel": true, "self": 14.255278629003328 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.719499995393562e-05, "count": 1, "self": 5.719499995393562e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 222.55101334396323, "count": 183047, "is_parallel": true, "self": 5.113883188958312, "children": { "process_trajectory": { "total": 128.60605327700495, "count": 183047, "is_parallel": true, "self": 128.20099624100504, "children": { "RLTrainer._checkpoint": { "total": 0.40505703599990284, "count": 2, "is_parallel": true, "self": 0.40505703599990284 } } }, "_update_policy": { "total": 88.83107687799998, "count": 45, "is_parallel": true, "self": 20.810598382998478, "children": { "TorchPPOOptimizer.update": { "total": 68.0204784950015, "count": 2292, "is_parallel": true, "self": 68.0204784950015 } } } } } } } } }, "TrainerController._save_models": { "total": 0.126322029999983, "count": 1, "self": 0.0008935390000033294, "children": { "RLTrainer._checkpoint": { "total": 0.12542849099997966, "count": 1, "self": 0.12542849099997966 } } } } } } }