{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5034646391868591, "min": 0.44306880235671997, "max": 2.796967029571533, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4818.15673828125, "min": 4537.09521484375, "max": 28674.505859375, "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": 12.44078254699707, "min": 0.4161001741886139, "max": 12.44078254699707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2425.95263671875, "min": 80.72343444824219, "max": 2518.72705078125, "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": 0.07514223079802011, "min": 0.06294433847187794, "max": 0.07514223079802011, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30056892319208045, "min": 0.25342130232014576, "max": 0.36119170095908504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18795302649046858, "min": 0.13101567421222615, "max": 0.3141874353967461, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7518121059618743, "min": 0.5240626968489046, "max": 1.5008130079390956, "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": 0.110776, "min": 0.110776, "max": 0.489176, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.443104, "min": 0.443104, "max": 2.34688, "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": 24.704545454545453, "min": 3.3636363636363638, "max": 24.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1087.0, "min": 148.0, "max": 1341.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.704545454545453, "min": 3.3636363636363638, "max": 24.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1087.0, "min": 148.0, "max": 1341.0, "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": "1682274666", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682275146" }, "total": 479.67850082100006, "count": 1, "self": 0.5774259090001124, "children": { "run_training.setup": { "total": 0.11175315999997792, "count": 1, "self": 0.11175315999997792 }, "TrainerController.start_learning": { "total": 478.98932175199997, "count": 1, "self": 0.5649310840085491, "children": { "TrainerController._reset_env": { "total": 4.7006287529999895, "count": 1, "self": 4.7006287529999895 }, "TrainerController.advance": { "total": 473.4794798539915, "count": 18214, "self": 0.27893431098522115, "children": { "env_step": { "total": 473.2005455430063, "count": 18214, "self": 342.87203616201714, "children": { "SubprocessEnvManager._take_step": { "total": 130.04834699399538, "count": 18214, "self": 1.6586528759960402, "children": { "TorchPolicy.evaluate": { "total": 128.38969411799934, "count": 18214, "self": 128.38969411799934 } } }, "workers": { "total": 0.2801623869937657, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 477.4673537560134, "count": 18214, "is_parallel": true, "self": 225.56550512501252, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004670622999981333, "count": 1, "is_parallel": true, "self": 0.003204200000027413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014664229999539202, "count": 10, "is_parallel": true, "self": 0.0014664229999539202 } } }, "UnityEnvironment.step": { "total": 0.07468854199998987, "count": 1, "is_parallel": true, "self": 0.0006517609999718843, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004276679999861699, "count": 1, "is_parallel": true, "self": 0.0004276679999861699 }, "communicator.exchange": { "total": 0.06621936999999889, "count": 1, "is_parallel": true, "self": 0.06621936999999889 }, "steps_from_proto": { "total": 0.007389743000032922, "count": 1, "is_parallel": true, "self": 0.0006579100000294602, "children": { "_process_rank_one_or_two_observation": { "total": 0.006731833000003462, "count": 10, "is_parallel": true, "self": 0.006731833000003462 } } } } } } }, "UnityEnvironment.step": { "total": 251.90184863100086, "count": 18213, "is_parallel": true, "self": 10.023365329007902, "children": { "UnityEnvironment._generate_step_input": { "total": 5.836196204992291, "count": 18213, "is_parallel": true, "self": 5.836196204992291 }, "communicator.exchange": { "total": 202.52322733799593, "count": 18213, "is_parallel": true, "self": 202.52322733799593 }, "steps_from_proto": { "total": 33.51905975900473, "count": 18213, "is_parallel": true, "self": 6.599159476023317, "children": { "_process_rank_one_or_two_observation": { "total": 26.919900282981416, "count": 182130, "is_parallel": true, "self": 26.919900282981416 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019125400001485104, "count": 1, "self": 0.00019125400001485104, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.6557142709946, "count": 428465, "is_parallel": true, "self": 10.552271645006442, "children": { "process_trajectory": { "total": 259.98662806698843, "count": 428465, "is_parallel": true, "self": 258.7754690819883, "children": { "RLTrainer._checkpoint": { "total": 1.211158985000111, "count": 4, "is_parallel": true, "self": 1.211158985000111 } } }, "_update_policy": { "total": 199.11681455899975, "count": 90, "is_parallel": true, "self": 70.83796451400099, "children": { "TorchPPOOptimizer.update": { "total": 128.27885004499876, "count": 4584, "is_parallel": true, "self": 128.27885004499876 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24409080699990682, "count": 1, "self": 0.0015469369999436822, "children": { "RLTrainer._checkpoint": { "total": 0.24254386999996314, "count": 1, "self": 0.24254386999996314 } } } } } } }