{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0469822883605957, "min": 1.0469822883605957, "max": 2.8557772636413574, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10031.1376953125, "min": 10031.1376953125, "max": 29340.255859375, "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": 12.48460578918457, "min": 0.2689879536628723, "max": 12.488801002502441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2434.498046875, "min": 52.18366241455078, "max": 2547.71533203125, "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": 0.0693885588814238, "min": 0.06158694351895475, "max": 0.07828786026438334, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2775542355256952, "min": 0.25391554467119826, "max": 0.35671742240026333, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22776683690209013, "min": 0.10075027478959264, "max": 0.2581299829716776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9110673476083605, "min": 0.40300109915837057, "max": 1.2882718963950288, "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": 24.477272727272727, "min": 2.772727272727273, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 122.0, "max": 1334.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 2.772727272727273, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 122.0, "max": 1334.0, "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": "1713360381", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713361049" }, "total": 668.1407053309999, "count": 1, "self": 0.6033382360000132, "children": { "run_training.setup": { "total": 0.10158858399995552, "count": 1, "self": 0.10158858399995552 }, "TrainerController.start_learning": { "total": 667.435778511, "count": 1, "self": 0.8514897800105246, "children": { "TrainerController._reset_env": { "total": 4.088136354000028, "count": 1, "self": 4.088136354000028 }, "TrainerController.advance": { "total": 662.3662340499894, "count": 18203, "self": 0.47045103898824436, "children": { "env_step": { "total": 661.8957830110012, "count": 18203, "self": 517.6222261279895, "children": { "SubprocessEnvManager._take_step": { "total": 143.82998309000436, "count": 18203, "self": 2.780755105014748, "children": { "TorchPolicy.evaluate": { "total": 141.0492279849896, "count": 18203, "self": 141.0492279849896 } } }, "workers": { "total": 0.44357379300731736, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 665.4499470920082, "count": 18203, "is_parallel": true, "self": 338.2799917139997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00940943599999855, "count": 1, "is_parallel": true, "self": 0.007508230000041749, "children": { "_process_rank_one_or_two_observation": { "total": 0.001901205999956801, "count": 10, "is_parallel": true, "self": 0.001901205999956801 } } }, "UnityEnvironment.step": { "total": 0.10242629399999714, "count": 1, "is_parallel": true, "self": 0.0011564009999460723, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043058199997858537, "count": 1, "is_parallel": true, "self": 0.00043058199997858537 }, "communicator.exchange": { "total": 0.09628039800003307, "count": 1, "is_parallel": true, "self": 0.09628039800003307 }, "steps_from_proto": { "total": 0.004558913000039411, "count": 1, "is_parallel": true, "self": 0.0005404810000300131, "children": { "_process_rank_one_or_two_observation": { "total": 0.004018432000009398, "count": 10, "is_parallel": true, "self": 0.004018432000009398 } } } } } } }, "UnityEnvironment.step": { "total": 327.16995537800847, "count": 18202, "is_parallel": true, "self": 15.627099309013545, "children": { "UnityEnvironment._generate_step_input": { "total": 7.783902933989566, "count": 18202, "is_parallel": true, "self": 7.783902933989566 }, "communicator.exchange": { "total": 257.9943698129996, "count": 18202, "is_parallel": true, "self": 257.9943698129996 }, "steps_from_proto": { "total": 45.76458332200576, "count": 18202, "is_parallel": true, "self": 9.23165441202434, "children": { "_process_rank_one_or_two_observation": { "total": 36.53292890998142, "count": 182020, "is_parallel": true, "self": 36.53292890998142 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018943199995646864, "count": 1, "self": 0.00018943199995646864, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 655.0455551000024, "count": 768232, "is_parallel": true, "self": 19.105085681971673, "children": { "process_trajectory": { "total": 340.681078265031, "count": 768232, "is_parallel": true, "self": 339.48991807203106, "children": { "RLTrainer._checkpoint": { "total": 1.1911601929999165, "count": 4, "is_parallel": true, "self": 1.1911601929999165 } } }, "_update_policy": { "total": 295.25939115299974, "count": 90, "is_parallel": true, "self": 61.57229061800672, "children": { "TorchPPOOptimizer.update": { "total": 233.68710053499302, "count": 4587, "is_parallel": true, "self": 233.68710053499302 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1297288949999711, "count": 1, "self": 0.0019327200000134326, "children": { "RLTrainer._checkpoint": { "total": 0.12779617499995766, "count": 1, "self": 0.12779617499995766 } } } } } } }