{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.038193702697754, "min": 1.030350923538208, "max": 2.8613169193267822, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9935.513671875, "min": 9935.513671875, "max": 29334.220703125, "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": 12.328165054321289, "min": 0.37729376554489136, "max": 12.328165054321289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2403.9921875, "min": 73.19499206542969, "max": 2487.3798828125, "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": 0.06662542372371308, "min": 0.06255266767866309, "max": 0.07364902402853249, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2665016948948523, "min": 0.25021067071465236, "max": 0.3600239780025018, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21088498173391118, "min": 0.11551465782423631, "max": 0.275950959909196, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8435399269356447, "min": 0.46205863129694524, "max": 1.37975479954598, "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": 24.5, "min": 3.1363636363636362, "max": 24.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1078.0, "min": 138.0, "max": 1335.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.5, "min": 3.1363636363636362, "max": 24.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1078.0, "min": 138.0, "max": 1335.0, "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": "1684980127", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684980586" }, "total": 459.224187163, "count": 1, "self": 0.7930568740000581, "children": { "run_training.setup": { "total": 0.042702440999960345, "count": 1, "self": 0.042702440999960345 }, "TrainerController.start_learning": { "total": 458.388427848, "count": 1, "self": 0.5340189850081742, "children": { "TrainerController._reset_env": { "total": 3.851602971000034, "count": 1, "self": 3.851602971000034 }, "TrainerController.advance": { "total": 453.78148916499174, "count": 18210, "self": 0.2589416989995925, "children": { "env_step": { "total": 453.52254746599215, "count": 18210, "self": 332.217590197989, "children": { "SubprocessEnvManager._take_step": { "total": 121.05866190100267, "count": 18210, "self": 1.6407698499895105, "children": { "TorchPolicy.evaluate": { "total": 119.41789205101315, "count": 18210, "self": 119.41789205101315 } } }, "workers": { "total": 0.24629536700047083, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 456.8339704130011, "count": 18210, "is_parallel": true, "self": 215.54992536099383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005236609000007775, "count": 1, "is_parallel": true, "self": 0.003811712000128864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014248969998789107, "count": 10, "is_parallel": true, "self": 0.0014248969998789107 } } }, "UnityEnvironment.step": { "total": 0.035692079000000376, "count": 1, "is_parallel": true, "self": 0.0006089469999324137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032056600002761115, "count": 1, "is_parallel": true, "self": 0.00032056600002761115 }, "communicator.exchange": { "total": 0.032587495000029776, "count": 1, "is_parallel": true, "self": 0.032587495000029776 }, "steps_from_proto": { "total": 0.0021750710000105755, "count": 1, "is_parallel": true, "self": 0.0003849539998554974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017901170001550781, "count": 10, "is_parallel": true, "self": 0.0017901170001550781 } } } } } } }, "UnityEnvironment.step": { "total": 241.2840450520073, "count": 18209, "is_parallel": true, "self": 9.51252943400948, "children": { "UnityEnvironment._generate_step_input": { "total": 5.100715559998321, "count": 18209, "is_parallel": true, "self": 5.100715559998321 }, "communicator.exchange": { "total": 194.34959157000242, "count": 18209, "is_parallel": true, "self": 194.34959157000242 }, "steps_from_proto": { "total": 32.32120848799707, "count": 18209, "is_parallel": true, "self": 6.112239286994509, "children": { "_process_rank_one_or_two_observation": { "total": 26.20896920100256, "count": 182090, "is_parallel": true, "self": 26.20896920100256 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014046800004052784, "count": 1, "self": 0.00014046800004052784, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.277419362983, "count": 429479, "is_parallel": true, "self": 9.714214477942278, "children": { "process_trajectory": { "total": 245.13627762804026, "count": 429479, "is_parallel": true, "self": 243.50793832804027, "children": { "RLTrainer._checkpoint": { "total": 1.6283392999999933, "count": 4, "is_parallel": true, "self": 1.6283392999999933 } } }, "_update_policy": { "total": 195.42692725700044, "count": 90, "is_parallel": true, "self": 76.11254794399963, "children": { "TorchPPOOptimizer.update": { "total": 119.31437931300081, "count": 4587, "is_parallel": true, "self": 119.31437931300081 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22117625900000348, "count": 1, "self": 0.0011386469999479232, "children": { "RLTrainer._checkpoint": { "total": 0.22003761200005556, "count": 1, "self": 0.22003761200005556 } } } } } } }