{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.109495759010315, "min": 1.109495759010315, "max": 2.8648905754089355, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10654.4873046875, "min": 10654.4873046875, "max": 29465.3984375, "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": 12.786986351013184, "min": 0.39018556475639343, "max": 12.786986351013184, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.46240234375, "min": 75.69599914550781, "max": 2581.293701171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07149481049133351, "min": 0.06052337364848891, "max": 0.0778180146962233, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28597924196533403, "min": 0.24209349459395563, "max": 0.36720735758610634, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.213619305368732, "min": 0.10804350982082314, "max": 0.27630090647760563, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.854477221474928, "min": 0.43217403928329257, "max": 1.3255834833664053, "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": 25.386363636363637, "min": 3.1818181818181817, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 140.0, "max": 1382.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.1818181818181817, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 140.0, "max": 1382.0, "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": "1679483654", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/aarriandiaga/anaconda3/envs/rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1679484215" }, "total": 560.3962161019444, "count": 1, "self": 0.37283196672797203, "children": { "run_training.setup": { "total": 0.013400740921497345, "count": 1, "self": 0.013400740921497345 }, "TrainerController.start_learning": { "total": 560.009983394295, "count": 1, "self": 0.3744734600186348, "children": { "TrainerController._reset_env": { "total": 4.812506929039955, "count": 1, "self": 4.812506929039955 }, "TrainerController.advance": { "total": 554.7010242640972, "count": 18209, "self": 0.19609463959932327, "children": { "env_step": { "total": 554.5049296244979, "count": 18209, "self": 473.3553622998297, "children": { "SubprocessEnvManager._take_step": { "total": 80.9631520062685, "count": 18209, "self": 1.161339569836855, "children": { "TorchPolicy.evaluate": { "total": 79.80181243643165, "count": 18209, "self": 79.80181243643165 } } }, "workers": { "total": 0.18641531839966774, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 558.8110276833177, "count": 18209, "is_parallel": true, "self": 199.96268732473254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004119589924812317, "count": 1, "is_parallel": true, "self": 0.0011003762483596802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030192136764526367, "count": 10, "is_parallel": true, "self": 0.0030192136764526367 } } }, "UnityEnvironment.step": { "total": 0.04341980069875717, "count": 1, "is_parallel": true, "self": 0.0008934885263442993, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005890838801860809, "count": 1, "is_parallel": true, "self": 0.0005890838801860809 }, "communicator.exchange": { "total": 0.03908456861972809, "count": 1, "is_parallel": true, "self": 0.03908456861972809 }, "steps_from_proto": { "total": 0.002852659672498703, "count": 1, "is_parallel": true, "self": 0.0006269253790378571, "children": { "_process_rank_one_or_two_observation": { "total": 0.002225734293460846, "count": 10, "is_parallel": true, "self": 0.002225734293460846 } } } } } } }, "UnityEnvironment.step": { "total": 358.8483403585851, "count": 18208, "is_parallel": true, "self": 15.237829092890024, "children": { "UnityEnvironment._generate_step_input": { "total": 8.073776423931122, "count": 18208, "is_parallel": true, "self": 8.073776423931122 }, "communicator.exchange": { "total": 287.9930094592273, "count": 18208, "is_parallel": true, "self": 287.9930094592273 }, "steps_from_proto": { "total": 47.54372538253665, "count": 18208, "is_parallel": true, "self": 9.056415759027004, "children": { "_process_rank_one_or_two_observation": { "total": 38.487309623509645, "count": 182080, "is_parallel": true, "self": 38.487309623509645 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014235079288482666, "count": 1, "self": 0.00014235079288482666, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 553.9420574568212, "count": 172943, "is_parallel": true, "self": 2.6755802631378174, "children": { "process_trajectory": { "total": 322.0033398345113, "count": 172943, "is_parallel": true, "self": 320.8285831809044, "children": { "RLTrainer._checkpoint": { "total": 1.1747566536068916, "count": 4, "is_parallel": true, "self": 1.1747566536068916 } } }, "_update_policy": { "total": 229.2631373591721, "count": 90, "is_parallel": true, "self": 40.4798436909914, "children": { "TorchPPOOptimizer.update": { "total": 188.7832936681807, "count": 4587, "is_parallel": true, "self": 188.7832936681807 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12183639034628868, "count": 1, "self": 0.0006985515356063843, "children": { "RLTrainer._checkpoint": { "total": 0.1211378388106823, "count": 1, "self": 0.1211378388106823 } } } } } } }