{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9128144979476929, "min": 0.9128144979476929, "max": 2.861827850341797, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8705.51171875, "min": 8705.51171875, "max": 29307.978515625, "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": 12.005651473999023, "min": 0.41671639680862427, "max": 12.005651473999023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2341.10205078125, "min": 80.84297943115234, "max": 2431.15380859375, "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": 0.07159733907239713, "min": 0.06567783662718354, "max": 0.07398088403370269, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2863893562895885, "min": 0.2642627494619685, "max": 0.36990442016851344, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20643348553601434, "min": 0.10890901241538242, "max": 0.29748959525250923, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8257339421440574, "min": 0.4356360496615297, "max": 1.425804939924502, "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": 23.34090909090909, "min": 3.409090909090909, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1027.0, "min": 150.0, "max": 1330.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.34090909090909, "min": 3.409090909090909, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1027.0, "min": 150.0, "max": 1330.0, "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": "1674120170", "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": "1674120604" }, "total": 433.989716823, "count": 1, "self": 0.3866189409999379, "children": { "run_training.setup": { "total": 0.1023443670000006, "count": 1, "self": 0.1023443670000006 }, "TrainerController.start_learning": { "total": 433.50075351500004, "count": 1, "self": 0.5381005430049868, "children": { "TrainerController._reset_env": { "total": 10.526599952000026, "count": 1, "self": 10.526599952000026 }, "TrainerController.advance": { "total": 422.31553445199495, "count": 18201, "self": 0.29915528598695573, "children": { "env_step": { "total": 422.016379166008, "count": 18201, "self": 278.03510491700575, "children": { "SubprocessEnvManager._take_step": { "total": 143.70629748999886, "count": 18201, "self": 1.4269688819997555, "children": { "TorchPolicy.evaluate": { "total": 142.2793286079991, "count": 18201, "self": 32.29766541900091, "children": { "TorchPolicy.sample_actions": { "total": 109.9816631889982, "count": 18201, "self": 109.9816631889982 } } } } }, "workers": { "total": 0.2749767590033798, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 432.19169745999216, "count": 18201, "is_parallel": true, "self": 207.13773102299746, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006926289999967139, "count": 1, "is_parallel": true, "self": 0.004266145000030974, "children": { "_process_rank_one_or_two_observation": { "total": 0.002660144999936165, "count": 10, "is_parallel": true, "self": 0.002660144999936165 } } }, "UnityEnvironment.step": { "total": 0.03759990899999366, "count": 1, "is_parallel": true, "self": 0.0003324689999999464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029525299999022536, "count": 1, "is_parallel": true, "self": 0.00029525299999022536 }, "communicator.exchange": { "total": 0.03533091700001023, "count": 1, "is_parallel": true, "self": 0.03533091700001023 }, "steps_from_proto": { "total": 0.0016412699999932556, "count": 1, "is_parallel": true, "self": 0.0003754819999812753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012657880000119803, "count": 10, "is_parallel": true, "self": 0.0012657880000119803 } } } } } } }, "UnityEnvironment.step": { "total": 225.0539664369947, "count": 18200, "is_parallel": true, "self": 8.509094083981495, "children": { "UnityEnvironment._generate_step_input": { "total": 4.922057198999312, "count": 18200, "is_parallel": true, "self": 4.922057198999312 }, "communicator.exchange": { "total": 181.59409689500603, "count": 18200, "is_parallel": true, "self": 181.59409689500603 }, "steps_from_proto": { "total": 30.02871825900786, "count": 18200, "is_parallel": true, "self": 6.613577991976399, "children": { "_process_rank_one_or_two_observation": { "total": 23.41514026703146, "count": 182000, "is_parallel": true, "self": 23.41514026703146 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.9713000091978756e-05, "count": 1, "self": 3.9713000091978756e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 419.38117719102314, "count": 343910, "is_parallel": true, "self": 8.9205669819857, "children": { "process_trajectory": { "total": 241.67264136103717, "count": 343910, "is_parallel": true, "self": 240.9633536680372, "children": { "RLTrainer._checkpoint": { "total": 0.7092876929999647, "count": 4, "is_parallel": true, "self": 0.7092876929999647 } } }, "_update_policy": { "total": 168.78796884800028, "count": 90, "is_parallel": true, "self": 40.40736239800253, "children": { "TorchPPOOptimizer.update": { "total": 128.38060644999774, "count": 4587, "is_parallel": true, "self": 128.38060644999774 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12047885499998756, "count": 1, "self": 0.0008570300000201314, "children": { "RLTrainer._checkpoint": { "total": 0.11962182499996743, "count": 1, "self": 0.11962182499996743 } } } } } } }