{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.73752760887146, "min": 0.73752760887146, "max": 2.8556318283081055, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7009.46240234375, "min": 7009.46240234375, "max": 29150.2890625, "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": 13.379960060119629, "min": 0.3564145565032959, "max": 13.405237197875977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2609.09228515625, "min": 69.14442443847656, "max": 2734.66845703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07251723696144302, "min": 0.058345733203197025, "max": 0.0750474076023024, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2900689478457721, "min": 0.2519760303410151, "max": 0.35262933768578525, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20613396438021286, "min": 0.11296369334313032, "max": 0.33287924668368174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8245358575208515, "min": 0.4518547733725213, "max": 1.6643962334184086, "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.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.Environment.CumulativeReward.mean": { "value": 25.704545454545453, "min": 3.1818181818181817, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 140.0, "max": 1442.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 3.1818181818181817, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 140.0, "max": 1442.0, "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": "1757771347", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757771789" }, "total": 442.1231500449999, "count": 1, "self": 0.4845805200000086, "children": { "run_training.setup": { "total": 0.026231634999930975, "count": 1, "self": 0.026231634999930975 }, "TrainerController.start_learning": { "total": 441.61233788999994, "count": 1, "self": 0.3699640140008569, "children": { "TrainerController._reset_env": { "total": 3.311346843000024, "count": 1, "self": 3.311346843000024 }, "TrainerController.advance": { "total": 437.8407842699992, "count": 18192, "self": 0.371938518062052, "children": { "env_step": { "total": 313.6376678959764, "count": 18192, "self": 242.30643367499965, "children": { "SubprocessEnvManager._take_step": { "total": 71.10682213699056, "count": 18192, "self": 1.2876580909969562, "children": { "TorchPolicy.evaluate": { "total": 69.8191640459936, "count": 18192, "self": 69.8191640459936 } } }, "workers": { "total": 0.22441208398618073, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 440.2164824350227, "count": 18192, "is_parallel": true, "self": 227.47080574701772, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00597949999996672, "count": 1, "is_parallel": true, "self": 0.004537281000011717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014422189999550028, "count": 10, "is_parallel": true, "self": 0.0014422189999550028 } } }, "UnityEnvironment.step": { "total": 0.04216669700008424, "count": 1, "is_parallel": true, "self": 0.0005804020001960453, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003684999999222782, "count": 1, "is_parallel": true, "self": 0.0003684999999222782 }, "communicator.exchange": { "total": 0.03892181400010486, "count": 1, "is_parallel": true, "self": 0.03892181400010486 }, "steps_from_proto": { "total": 0.002295980999861058, "count": 1, "is_parallel": true, "self": 0.0004607399996530148, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018352410002080433, "count": 10, "is_parallel": true, "self": 0.0018352410002080433 } } } } } } }, "UnityEnvironment.step": { "total": 212.745676688005, "count": 18191, "is_parallel": true, "self": 10.044704356051852, "children": { "UnityEnvironment._generate_step_input": { "total": 5.789824115990996, "count": 18191, "is_parallel": true, "self": 5.789824115990996 }, "communicator.exchange": { "total": 163.29265977399996, "count": 18191, "is_parallel": true, "self": 163.29265977399996 }, "steps_from_proto": { "total": 33.6184884419622, "count": 18191, "is_parallel": true, "self": 5.881282465886898, "children": { "_process_rank_one_or_two_observation": { "total": 27.737205976075302, "count": 181910, "is_parallel": true, "self": 27.737205976075302 } } } } } } } } } } }, "trainer_advance": { "total": 123.83117785596073, "count": 18192, "self": 0.45918509997227375, "children": { "process_trajectory": { "total": 28.00629032898746, "count": 18192, "self": 27.562720691987124, "children": { "RLTrainer._checkpoint": { "total": 0.443569637000337, "count": 4, "self": 0.443569637000337 } } }, "_update_policy": { "total": 95.365702427001, "count": 90, "self": 39.88826423000273, "children": { "TorchPPOOptimizer.update": { "total": 55.477438196998264, "count": 4587, "self": 55.477438196998264 } } } } } } }, "trainer_threads": { "total": 9.809998573473422e-07, "count": 1, "self": 9.809998573473422e-07 }, "TrainerController._save_models": { "total": 0.09024178200002098, "count": 1, "self": 0.0008383189999676688, "children": { "RLTrainer._checkpoint": { "total": 0.08940346300005331, "count": 1, "self": 0.08940346300005331 } } } } } } }