{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6309082508087158, "min": 0.5099654793739319, "max": 2.8621561527252197, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6475.01123046875, "min": 5001.62744140625, "max": 29279.857421875, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.23983383178711, "min": 0.48367467522621155, "max": 14.437265396118164, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2919.166015625, "min": 93.8328857421875, "max": 2950.404541015625, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06644027113581222, "min": 0.05646135654573228, "max": 0.07753355630842385, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3322013556790611, "min": 0.22584542618292913, "max": 0.3876677815421192, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14481044218820685, "min": 0.12490951724227188, "max": 0.2960522689801805, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7240522109410342, "min": 0.4996380689690875, "max": 1.3931378752869719, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.181818181818183, "min": 3.6136363636363638, "max": 28.563636363636363, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1550.0, "min": 159.0, "max": 1571.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.181818181818183, "min": 3.6136363636363638, "max": 28.563636363636363, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1550.0, "min": 159.0, "max": 1571.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722514920", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722520057" }, "total": 5137.440083906, "count": 1, "self": 0.8017822199990405, "children": { "run_training.setup": { "total": 0.07656488500003888, "count": 1, "self": 0.07656488500003888 }, "TrainerController.start_learning": { "total": 5136.561736801001, "count": 1, "self": 7.192904500968325, "children": { "TrainerController._reset_env": { "total": 2.989861184999995, "count": 1, "self": 2.989861184999995 }, "TrainerController.advance": { "total": 5126.235490562031, "count": 181878, "self": 3.6519696678678883, "children": { "env_step": { "total": 5122.5835208941635, "count": 181878, "self": 3363.4786690350493, "children": { "SubprocessEnvManager._take_step": { "total": 1755.2682125220467, "count": 181878, "self": 17.842771185969923, "children": { "TorchPolicy.evaluate": { "total": 1737.4254413360768, "count": 181878, "self": 1737.4254413360768 } } }, "workers": { "total": 3.8366393370674814, "count": 181878, "self": 0.0, "children": { "worker_root": { "total": 5122.055832098047, "count": 181878, "is_parallel": true, "self": 2546.7344558391305, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007085079000034966, "count": 1, "is_parallel": true, "self": 0.00460658300016803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024784959998669365, "count": 10, "is_parallel": true, "self": 0.0024784959998669365 } } }, "UnityEnvironment.step": { "total": 0.05071494599997095, "count": 1, "is_parallel": true, "self": 0.0007153289999450863, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005095300000448333, "count": 1, "is_parallel": true, "self": 0.0005095300000448333 }, "communicator.exchange": { "total": 0.046944252999992386, "count": 1, "is_parallel": true, "self": 0.046944252999992386 }, "steps_from_proto": { "total": 0.002545833999988645, "count": 1, "is_parallel": true, "self": 0.0004121069998745952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021337270001140496, "count": 10, "is_parallel": true, "self": 0.0021337270001140496 } } } } } } }, "UnityEnvironment.step": { "total": 2575.3213762589166, "count": 181877, "is_parallel": true, "self": 115.50600597202492, "children": { "UnityEnvironment._generate_step_input": { "total": 61.06947474596154, "count": 181877, "is_parallel": true, "self": 61.06947474596154 }, "communicator.exchange": { "total": 2012.721372446055, "count": 181877, "is_parallel": true, "self": 2012.721372446055 }, "steps_from_proto": { "total": 386.02452309487546, "count": 181877, "is_parallel": true, "self": 76.59406713223643, "children": { "_process_rank_one_or_two_observation": { "total": 309.43045596263903, "count": 1818770, "is_parallel": true, "self": 309.43045596263903 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003388760005691438, "count": 1, "self": 0.0003388760005691438, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 5063.5507270832295, "count": 7459669, "is_parallel": true, "self": 165.32681265251995, "children": { "process_trajectory": { "total": 2800.998698407716, "count": 7459669, "is_parallel": true, "self": 2792.9329449067145, "children": { "RLTrainer._checkpoint": { "total": 8.065753501001268, "count": 40, "is_parallel": true, "self": 8.065753501001268 } } }, "_update_policy": { "total": 2097.2252160229937, "count": 909, "is_parallel": true, "self": 661.6365035509252, "children": { "TorchPPOOptimizer.update": { "total": 1435.5887124720684, "count": 46350, "is_parallel": true, "self": 1435.5887124720684 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14314167700013058, "count": 1, "self": 0.0015532860006715055, "children": { "RLTrainer._checkpoint": { "total": 0.14158839099945908, "count": 1, "self": 0.14158839099945908 } } } } } } }