{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8804407119750977, "min": 0.8804407119750977, "max": 2.8629486560821533, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8416.1328125, "min": 8416.1328125, "max": 29350.94921875, "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": 12.862289428710938, "min": 0.2859894931316376, "max": 12.911805152893066, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.146484375, "min": 55.48196029663086, "max": 2634.00830078125, "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": 0.06442618026188689, "min": 0.06327610562267878, "max": 0.0744403078382425, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25770472104754755, "min": 0.25770472104754755, "max": 0.3557669647624625, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17670923234054856, "min": 0.11889948357608827, "max": 0.29527008071833966, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7068369293621942, "min": 0.4755979343043531, "max": 1.4763504035916983, "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": 24.84090909090909, "min": 3.2045454545454546, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 141.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 3.2045454545454546, "max": 25.254545454545454, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 141.0, "max": 1389.0, "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": "1701333821", "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", "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": "1701334297" }, "total": 476.0004965520002, "count": 1, "self": 0.4388839610001014, "children": { "run_training.setup": { "total": 0.06036021299996719, "count": 1, "self": 0.06036021299996719 }, "TrainerController.start_learning": { "total": 475.5012523780001, "count": 1, "self": 0.5758853250026732, "children": { "TrainerController._reset_env": { "total": 3.379580941000313, "count": 1, "self": 3.379580941000313 }, "TrainerController.advance": { "total": 471.4605126239976, "count": 18200, "self": 0.28750222094731726, "children": { "env_step": { "total": 471.1730104030503, "count": 18200, "self": 318.9512209329682, "children": { "SubprocessEnvManager._take_step": { "total": 151.92091887602692, "count": 18200, "self": 1.4836510300651753, "children": { "TorchPolicy.evaluate": { "total": 150.43726784596174, "count": 18200, "self": 150.43726784596174 } } }, "workers": { "total": 0.3008705940551408, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 474.20142997396806, "count": 18200, "is_parallel": true, "self": 233.54264314396687, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050040529999932915, "count": 1, "is_parallel": true, "self": 0.0034830170002351224, "children": { "_process_rank_one_or_two_observation": { "total": 0.001521035999758169, "count": 10, "is_parallel": true, "self": 0.001521035999758169 } } }, "UnityEnvironment.step": { "total": 0.08605631699992955, "count": 1, "is_parallel": true, "self": 0.0006433849998757069, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000452558999768371, "count": 1, "is_parallel": true, "self": 0.000452558999768371 }, "communicator.exchange": { "total": 0.08279740200032393, "count": 1, "is_parallel": true, "self": 0.08279740200032393 }, "steps_from_proto": { "total": 0.0021629709999615443, "count": 1, "is_parallel": true, "self": 0.00041247900071539334, "children": { "_process_rank_one_or_two_observation": { "total": 0.001750491999246151, "count": 10, "is_parallel": true, "self": 0.001750491999246151 } } } } } } }, "UnityEnvironment.step": { "total": 240.6587868300012, "count": 18199, "is_parallel": true, "self": 10.650127033955414, "children": { "UnityEnvironment._generate_step_input": { "total": 5.379149491936914, "count": 18199, "is_parallel": true, "self": 5.379149491936914 }, "communicator.exchange": { "total": 190.5002978760781, "count": 18199, "is_parallel": true, "self": 190.5002978760781 }, "steps_from_proto": { "total": 34.12921242803077, "count": 18199, "is_parallel": true, "self": 6.44786305505022, "children": { "_process_rank_one_or_two_observation": { "total": 27.68134937298055, "count": 181990, "is_parallel": true, "self": 27.68134937298055 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014102199975241092, "count": 1, "self": 0.00014102199975241092, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.4720485238681, "count": 491746, "is_parallel": true, "self": 10.474638875927667, "children": { "process_trajectory": { "total": 263.443880561937, "count": 491746, "is_parallel": true, "self": 262.9603323189376, "children": { "RLTrainer._checkpoint": { "total": 0.48354824299940447, "count": 4, "is_parallel": true, "self": 0.48354824299940447 } } }, "_update_policy": { "total": 193.55352908600344, "count": 90, "is_parallel": true, "self": 60.09639641599006, "children": { "TorchPPOOptimizer.update": { "total": 133.45713267001338, "count": 4587, "is_parallel": true, "self": 133.45713267001338 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0851324659997772, "count": 1, "self": 0.0008769420001044637, "children": { "RLTrainer._checkpoint": { "total": 0.08425552399967273, "count": 1, "self": 0.08425552399967273 } } } } } } }