{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9344552755355835, "min": 0.9344552755355835, "max": 2.8631434440612793, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8963.294921875, "min": 8963.294921875, "max": 29321.451171875, "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": 12.675688743591309, "min": 0.4464792013168335, "max": 12.726126670837402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2471.75927734375, "min": 86.6169662475586, "max": 2596.1298828125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0670316672398008, "min": 0.05922055003497471, "max": 0.07344016153345757, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2681266689592032, "min": 0.23688220013989883, "max": 0.35536470815828114, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22494573365239534, "min": 0.14679418645990902, "max": 0.27767438353861074, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8997829346095814, "min": 0.5871767458396361, "max": 1.3558914488838878, "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": 24.568181818181817, "min": 3.8181818181818183, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 168.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.568181818181817, "min": 3.8181818181818183, "max": 25.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 168.0, "max": 1398.0, "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": "1718798592", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/dqn.yml --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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718799059" }, "total": 467.66780147399993, "count": 1, "self": 0.807721590999904, "children": { "run_training.setup": { "total": 0.05457084100009979, "count": 1, "self": 0.05457084100009979 }, "TrainerController.start_learning": { "total": 466.8055090419999, "count": 1, "self": 0.6315943390072789, "children": { "TrainerController._reset_env": { "total": 2.9989314599999943, "count": 1, "self": 2.9989314599999943 }, "TrainerController.advance": { "total": 463.0313217799927, "count": 18211, "self": 0.3025476249874828, "children": { "env_step": { "total": 462.7287741550052, "count": 18211, "self": 298.8182257409961, "children": { "SubprocessEnvManager._take_step": { "total": 163.60380878999763, "count": 18211, "self": 1.557970495991981, "children": { "TorchPolicy.evaluate": { "total": 162.04583829400565, "count": 18211, "self": 162.04583829400565 } } }, "workers": { "total": 0.30673962401147037, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 465.4065981050111, "count": 18211, "is_parallel": true, "self": 234.79293510099865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005869852000046194, "count": 1, "is_parallel": true, "self": 0.00434121199987203, "children": { "_process_rank_one_or_two_observation": { "total": 0.001528640000174164, "count": 10, "is_parallel": true, "self": 0.001528640000174164 } } }, "UnityEnvironment.step": { "total": 0.03721399599999131, "count": 1, "is_parallel": true, "self": 0.0006845399999519941, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004549820000647742, "count": 1, "is_parallel": true, "self": 0.0004549820000647742 }, "communicator.exchange": { "total": 0.033832809999921665, "count": 1, "is_parallel": true, "self": 0.033832809999921665 }, "steps_from_proto": { "total": 0.0022416640000528787, "count": 1, "is_parallel": true, "self": 0.0006585710000308609, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015830930000220178, "count": 10, "is_parallel": true, "self": 0.0015830930000220178 } } } } } } }, "UnityEnvironment.step": { "total": 230.61366300401244, "count": 18210, "is_parallel": true, "self": 10.455484512025578, "children": { "UnityEnvironment._generate_step_input": { "total": 5.547299315998885, "count": 18210, "is_parallel": true, "self": 5.547299315998885 }, "communicator.exchange": { "total": 180.40194074899216, "count": 18210, "is_parallel": true, "self": 180.40194074899216 }, "steps_from_proto": { "total": 34.208938426995815, "count": 18210, "is_parallel": true, "self": 6.561433929023565, "children": { "_process_rank_one_or_two_observation": { "total": 27.64750449797225, "count": 182100, "is_parallel": true, "self": 27.64750449797225 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017572399997334287, "count": 1, "self": 0.00017572399997334287, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.4388389169811, "count": 693812, "is_parallel": true, "self": 14.424746132022733, "children": { "process_trajectory": { "total": 252.10034478795853, "count": 693812, "is_parallel": true, "self": 250.7391300039584, "children": { "RLTrainer._checkpoint": { "total": 1.3612147840001398, "count": 4, "is_parallel": true, "self": 1.3612147840001398 } } }, "_update_policy": { "total": 190.91374799699986, "count": 90, "is_parallel": true, "self": 59.10216696799978, "children": { "TorchPPOOptimizer.update": { "total": 131.81158102900008, "count": 4584, "is_parallel": true, "self": 131.81158102900008 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14348573899997064, "count": 1, "self": 0.0013715370000682015, "children": { "RLTrainer._checkpoint": { "total": 0.14211420199990243, "count": 1, "self": 0.14211420199990243 } } } } } } }