{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6764739751815796, "min": 1.6764739751815796, "max": 2.866486072540283, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17205.65234375, "min": 16948.794921875, "max": 29387.21484375, "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": 9.173157691955566, "min": 0.4863477349281311, "max": 9.173157691955566, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1871.32421875, "min": 94.3514633178711, "max": 1871.32421875, "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": 0.06968677886807378, "min": 0.06376685807743912, "max": 0.07281882597439393, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3484338943403689, "min": 0.27031372345164506, "max": 0.35862929481435474, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2490031106214897, "min": 0.12580272104070686, "max": 0.2940695539262949, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2450155531074485, "min": 0.5032108841628274, "max": 1.4035430988844704, "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": 19.418181818181818, "min": 3.772727272727273, "max": 19.418181818181818, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1068.0, "min": 166.0, "max": 1068.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.418181818181818, "min": 3.772727272727273, "max": 19.418181818181818, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1068.0, "min": 166.0, "max": 1068.0, "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": "1675143011", "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": "1675143278" }, "total": 267.1985703600001, "count": 1, "self": 0.4408134479999717, "children": { "run_training.setup": { "total": 0.11868147899997439, "count": 1, "self": 0.11868147899997439 }, "TrainerController.start_learning": { "total": 266.63907543300013, "count": 1, "self": 0.38223843198659324, "children": { "TrainerController._reset_env": { "total": 11.006197052000061, "count": 1, "self": 11.006197052000061 }, "TrainerController.advance": { "total": 255.10343277301354, "count": 9134, "self": 0.19574474000035025, "children": { "env_step": { "total": 254.9076880330132, "count": 9134, "self": 168.51113590900513, "children": { "SubprocessEnvManager._take_step": { "total": 86.22188644299627, "count": 9134, "self": 0.9243565759949206, "children": { "TorchPolicy.evaluate": { "total": 85.29752986700134, "count": 9134, "self": 19.708890706000147, "children": { "TorchPolicy.sample_actions": { "total": 65.5886391610012, "count": 9134, "self": 65.5886391610012 } } } } }, "workers": { "total": 0.17466568101178837, "count": 9134, "self": 0.0, "children": { "worker_root": { "total": 265.65057478199844, "count": 9134, "is_parallel": true, "self": 126.68988286400179, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006308463999971536, "count": 1, "is_parallel": true, "self": 0.0037249230001634714, "children": { "_process_rank_one_or_two_observation": { "total": 0.002583540999808065, "count": 10, "is_parallel": true, "self": 0.002583540999808065 } } }, "UnityEnvironment.step": { "total": 0.07085379199997988, "count": 1, "is_parallel": true, "self": 0.0007382140000800064, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004352179998932115, "count": 1, "is_parallel": true, "self": 0.0004352179998932115 }, "communicator.exchange": { "total": 0.0675956339999857, "count": 1, "is_parallel": true, "self": 0.0675956339999857 }, "steps_from_proto": { "total": 0.0020847260000209644, "count": 1, "is_parallel": true, "self": 0.0004811119998748836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016036140001460808, "count": 10, "is_parallel": true, "self": 0.0016036140001460808 } } } } } } }, "UnityEnvironment.step": { "total": 138.96069191799666, "count": 9133, "is_parallel": true, "self": 5.264096832985388, "children": { "UnityEnvironment._generate_step_input": { "total": 2.960385071995688, "count": 9133, "is_parallel": true, "self": 2.960385071995688 }, "communicator.exchange": { "total": 112.69907575201023, "count": 9133, "is_parallel": true, "self": 112.69907575201023 }, "steps_from_proto": { "total": 18.03713426100535, "count": 9133, "is_parallel": true, "self": 4.2189366359936, "children": { "_process_rank_one_or_two_observation": { "total": 13.818197625011749, "count": 91330, "is_parallel": true, "self": 13.818197625011749 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.0840000085372594e-05, "count": 1, "self": 5.0840000085372594e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 253.1582427568984, "count": 221425, "is_parallel": true, "self": 6.118423376877104, "children": { "process_trajectory": { "total": 146.96642901202097, "count": 221425, "is_parallel": true, "self": 146.5562795660211, "children": { "RLTrainer._checkpoint": { "total": 0.41014944599987757, "count": 2, "is_parallel": true, "self": 0.41014944599987757 } } }, "_update_policy": { "total": 100.07339036800033, "count": 45, "is_parallel": true, "self": 24.667747799007884, "children": { "TorchPPOOptimizer.update": { "total": 75.40564256899245, "count": 2292, "is_parallel": true, "self": 75.40564256899245 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14715633599985267, "count": 1, "self": 0.0010198879997460608, "children": { "RLTrainer._checkpoint": { "total": 0.1461364480001066, "count": 1, "self": 0.1461364480001066 } } } } } } }