{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.712080717086792, "min": 2.712080717086792, "max": 2.8536224365234375, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 27923.58203125, "min": 27923.58203125, "max": 29129.77734375, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.410117506980896, "min": 0.3220275342464447, "max": 1.410117506980896, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 289.0740966796875, "min": 62.47333908081055, "max": 289.0740966796875, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06754010982398291, "min": 0.0605371213320063, "max": 0.06754010982398291, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33770054911991454, "min": 0.2421484853280252, "max": 0.33770054911991454, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2123546910928745, "min": 0.11763942620360895, "max": 0.2123546910928745, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0617734554643725, "min": 0.4705577048144358, "max": 1.0617734554643725, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.963636363636364, "min": 3.1818181818181817, "max": 5.963636363636364, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 328.0, "min": 140.0, "max": 328.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.963636363636364, "min": 3.1818181818181817, "max": 5.963636363636364, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 328.0, "min": 140.0, "max": 328.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1750162863", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn 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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750162913" }, "total": 50.33321677199996, "count": 1, "self": 0.7077793039999847, "children": { "run_training.setup": { "total": 0.032390044999999645, "count": 1, "self": 0.032390044999999645 }, "TrainerController.start_learning": { "total": 49.59304742299997, "count": 1, "self": 0.03362457099984795, "children": { "TrainerController._reset_env": { "total": 3.385959603999993, "count": 1, "self": 3.385959603999993 }, "TrainerController.advance": { "total": 46.09343667500008, "count": 1864, "self": 0.03547041999894418, "children": { "env_step": { "total": 30.273440180000705, "count": 1864, "self": 23.140266421003616, "children": { "SubprocessEnvManager._take_step": { "total": 7.112640975999454, "count": 1864, "self": 0.12895833899830222, "children": { "TorchPolicy.evaluate": { "total": 6.983682637001152, "count": 1864, "self": 6.983682637001152 } } }, "workers": { "total": 0.020532782997634058, "count": 1864, "self": 0.0, "children": { "worker_root": { "total": 49.06874965900158, "count": 1864, "is_parallel": true, "self": 28.73543460699966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006090546999985236, "count": 1, "is_parallel": true, "self": 0.0040916110000353, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019989359999499356, "count": 10, "is_parallel": true, "self": 0.0019989359999499356 } } }, "UnityEnvironment.step": { "total": 0.03771642899999961, "count": 1, "is_parallel": true, "self": 0.00060368100002961, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039783599999054786, "count": 1, "is_parallel": true, "self": 0.00039783599999054786 }, "communicator.exchange": { "total": 0.03487446799999816, "count": 1, "is_parallel": true, "self": 0.03487446799999816 }, "steps_from_proto": { "total": 0.0018404439999812894, "count": 1, "is_parallel": true, "self": 0.00034672600003204934, "children": { "_process_rank_one_or_two_observation": { "total": 0.00149371799994924, "count": 10, "is_parallel": true, "self": 0.00149371799994924 } } } } } } }, "UnityEnvironment.step": { "total": 20.33331505200192, "count": 1863, "is_parallel": true, "self": 0.9978730200008954, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5596543690021463, "count": 1863, "is_parallel": true, "self": 0.5596543690021463 }, "communicator.exchange": { "total": 15.487817837999046, "count": 1863, "is_parallel": true, "self": 15.487817837999046 }, "steps_from_proto": { "total": 3.287969824999834, "count": 1863, "is_parallel": true, "self": 0.5733251129974519, "children": { "_process_rank_one_or_two_observation": { "total": 2.714644712002382, "count": 18630, "is_parallel": true, "self": 2.714644712002382 } } } } } } } } } } }, "trainer_advance": { "total": 15.784526075000429, "count": 1864, "self": 0.044918223999843576, "children": { "process_trajectory": { "total": 6.384422887000426, "count": 1864, "self": 2.8404975750005974, "children": { "RLTrainer._checkpoint": { "total": 3.5439253119998284, "count": 41, "self": 3.5439253119998284 } } }, "_update_policy": { "total": 9.35518496400016, "count": 9, "self": 3.8752314460022603, "children": { "TorchPPOOptimizer.update": { "total": 5.479953517997899, "count": 456, "self": 5.479953517997899 } } } } } } }, "trainer_threads": { "total": 8.819999948173063e-07, "count": 1, "self": 8.819999948173063e-07 }, "TrainerController._save_models": { "total": 0.08002569100005985, "count": 1, "self": 0.0008977760001016577, "children": { "RLTrainer._checkpoint": { "total": 0.0791279149999582, "count": 1, "self": 0.0791279149999582 } } } } } } }