{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9399150013923645, "min": 0.9399150013923645, "max": 2.8670413494110107, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8974.30859375, "min": 8974.30859375, "max": 29487.521484375, "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": 13.005203247070312, "min": 0.3469875752925873, "max": 13.005203247070312, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.0146484375, "min": 67.31558990478516, "max": 2645.926025390625, "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": 0.06673289035796759, "min": 0.06093570566133399, "max": 0.07264777803299927, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26693156143187036, "min": 0.24374282264533595, "max": 0.36323889016499633, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20402495745642513, "min": 0.13404868671661424, "max": 0.3005102521502504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8160998298257005, "min": 0.536194746866457, "max": 1.44481550273942, "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": 25.431818181818183, "min": 3.840909090909091, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 169.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.840909090909091, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 169.0, "max": 1415.0, "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": "1693995107", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693995580" }, "total": 473.5315992499999, "count": 1, "self": 0.43785064199994395, "children": { "run_training.setup": { "total": 0.06779819799999132, "count": 1, "self": 0.06779819799999132 }, "TrainerController.start_learning": { "total": 473.02595040999995, "count": 1, "self": 0.5601141980021112, "children": { "TrainerController._reset_env": { "total": 4.191706034000049, "count": 1, "self": 4.191706034000049 }, "TrainerController.advance": { "total": 468.1369509229979, "count": 18202, "self": 0.27569374999995944, "children": { "env_step": { "total": 467.86125717299797, "count": 18202, "self": 341.5541262439858, "children": { "SubprocessEnvManager._take_step": { "total": 126.01009894301046, "count": 18202, "self": 1.9302890779886184, "children": { "TorchPolicy.evaluate": { "total": 124.07980986502184, "count": 18202, "self": 124.07980986502184 } } }, "workers": { "total": 0.29703198600168434, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 471.5679809819944, "count": 18202, "is_parallel": true, "self": 223.28026663598507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005809059000057459, "count": 1, "is_parallel": true, "self": 0.004323058000295532, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014860009997619272, "count": 10, "is_parallel": true, "self": 0.0014860009997619272 } } }, "UnityEnvironment.step": { "total": 0.0351729129999967, "count": 1, "is_parallel": true, "self": 0.000611493000064911, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003104319999920335, "count": 1, "is_parallel": true, "self": 0.0003104319999920335 }, "communicator.exchange": { "total": 0.032036157999982606, "count": 1, "is_parallel": true, "self": 0.032036157999982606 }, "steps_from_proto": { "total": 0.0022148299999571464, "count": 1, "is_parallel": true, "self": 0.0004015859999526583, "children": { "_process_rank_one_or_two_observation": { "total": 0.001813244000004488, "count": 10, "is_parallel": true, "self": 0.001813244000004488 } } } } } } }, "UnityEnvironment.step": { "total": 248.28771434600935, "count": 18201, "is_parallel": true, "self": 10.431011325975078, "children": { "UnityEnvironment._generate_step_input": { "total": 5.34731825901747, "count": 18201, "is_parallel": true, "self": 5.34731825901747 }, "communicator.exchange": { "total": 196.97000593201096, "count": 18201, "is_parallel": true, "self": 196.97000593201096 }, "steps_from_proto": { "total": 35.53937882900584, "count": 18201, "is_parallel": true, "self": 6.313945905062269, "children": { "_process_rank_one_or_two_observation": { "total": 29.225432923943572, "count": 182010, "is_parallel": true, "self": 29.225432923943572 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018875799992201792, "count": 1, "self": 0.00018875799992201792, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.699954364972, "count": 430320, "is_parallel": true, "self": 9.532360669014679, "children": { "process_trajectory": { "total": 252.91414222095761, "count": 430320, "is_parallel": true, "self": 251.60596514295764, "children": { "RLTrainer._checkpoint": { "total": 1.3081770779999715, "count": 4, "is_parallel": true, "self": 1.3081770779999715 } } }, "_update_policy": { "total": 202.25345147499968, "count": 90, "is_parallel": true, "self": 81.2340084559961, "children": { "TorchPPOOptimizer.update": { "total": 121.01944301900357, "count": 4584, "is_parallel": true, "self": 121.01944301900357 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13699049699994248, "count": 1, "self": 0.0009042690001024312, "children": { "RLTrainer._checkpoint": { "total": 0.13608622799984005, "count": 1, "self": 0.13608622799984005 } } } } } } }