{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9353621602058411, "min": 0.9353621602058411, "max": 2.8643124103546143, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8930.837890625, "min": 8930.837890625, "max": 29333.423828125, "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": 12.753926277160645, "min": 0.24486985802650452, "max": 12.753926277160645, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2487.015625, "min": 47.50475311279297, "max": 2554.7646484375, "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": 0.06647700000658184, "min": 0.05969474353980474, "max": 0.07528391092794254, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26590800002632736, "min": 0.26590800002632736, "max": 0.37440616414217703, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19717320631824287, "min": 0.1080628109835636, "max": 0.27370550235112506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7886928252729715, "min": 0.4322512439342544, "max": 1.3685275117556253, "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": 25.818181818181817, "min": 3.2045454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 141.0, "max": 1376.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.2045454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 141.0, "max": 1376.0, "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": "1673447984", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1673448405" }, "total": 420.77541457399997, "count": 1, "self": 0.43600791199997957, "children": { "run_training.setup": { "total": 0.11323907500002406, "count": 1, "self": 0.11323907500002406 }, "TrainerController.start_learning": { "total": 420.22616758699996, "count": 1, "self": 0.5057763289950117, "children": { "TrainerController._reset_env": { "total": 6.781906037999988, "count": 1, "self": 6.781906037999988 }, "TrainerController.advance": { "total": 412.81946261400503, "count": 18204, "self": 0.25631104600972776, "children": { "env_step": { "total": 412.5631515679953, "count": 18204, "self": 268.49138263400727, "children": { "SubprocessEnvManager._take_step": { "total": 143.81712610299502, "count": 18204, "self": 1.444625849994054, "children": { "TorchPolicy.evaluate": { "total": 142.37250025300096, "count": 18204, "self": 31.222968704008338, "children": { "TorchPolicy.sample_actions": { "total": 111.14953154899263, "count": 18204, "self": 111.14953154899263 } } } } }, "workers": { "total": 0.25464283099302065, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 419.1054510809901, "count": 18204, "is_parallel": true, "self": 204.38549716397694, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00582484600005273, "count": 1, "is_parallel": true, "self": 0.0034945070001413114, "children": { "_process_rank_one_or_two_observation": { "total": 0.002330338999911419, "count": 10, "is_parallel": true, "self": 0.002330338999911419 } } }, "UnityEnvironment.step": { "total": 0.04287225899997793, "count": 1, "is_parallel": true, "self": 0.0003968949999944016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002636479999864605, "count": 1, "is_parallel": true, "self": 0.0002636479999864605 }, "communicator.exchange": { "total": 0.0403199869999753, "count": 1, "is_parallel": true, "self": 0.0403199869999753 }, "steps_from_proto": { "total": 0.001891729000021769, "count": 1, "is_parallel": true, "self": 0.0004310900002906237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014606389997311453, "count": 10, "is_parallel": true, "self": 0.0014606389997311453 } } } } } } }, "UnityEnvironment.step": { "total": 214.71995391701319, "count": 18203, "is_parallel": true, "self": 8.190866097010485, "children": { "UnityEnvironment._generate_step_input": { "total": 4.778878550996183, "count": 18203, "is_parallel": true, "self": 4.778878550996183 }, "communicator.exchange": { "total": 172.2780343470077, "count": 18203, "is_parallel": true, "self": 172.2780343470077 }, "steps_from_proto": { "total": 29.47217492199883, "count": 18203, "is_parallel": true, "self": 6.240823847969807, "children": { "_process_rank_one_or_two_observation": { "total": 23.23135107402902, "count": 182030, "is_parallel": true, "self": 23.23135107402902 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.430399997090717e-05, "count": 1, "self": 4.430399997090717e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 410.0213472689715, "count": 331610, "is_parallel": true, "self": 8.736266929979877, "children": { "process_trajectory": { "total": 233.99930441399147, "count": 331610, "is_parallel": true, "self": 233.2105148499915, "children": { "RLTrainer._checkpoint": { "total": 0.7887895639999556, "count": 4, "is_parallel": true, "self": 0.7887895639999556 } } }, "_update_policy": { "total": 167.28577592500017, "count": 90, "is_parallel": true, "self": 43.12495777200189, "children": { "TorchPPOOptimizer.update": { "total": 124.16081815299827, "count": 4587, "is_parallel": true, "self": 124.16081815299827 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11897830199995951, "count": 1, "self": 0.0008569739999302328, "children": { "RLTrainer._checkpoint": { "total": 0.11812132800002928, "count": 1, "self": 0.11812132800002928 } } } } } } }