{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9339746832847595, "min": 0.9339746832847595, "max": 2.867868661880493, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8938.1376953125, "min": 8938.1376953125, "max": 29401.390625, "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": 12.950075149536133, "min": 0.4277137815952301, "max": 12.950075149536133, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.2646484375, "min": 82.97647094726562, "max": 2630.16650390625, "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": 0.0697958040553239, "min": 0.06018964309366899, "max": 0.07421633428741331, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2791832162212956, "min": 0.24075857237467596, "max": 0.36709470318800963, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21199633356402903, "min": 0.11488528360667474, "max": 0.2699850071878994, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8479853342561161, "min": 0.45954113442669897, "max": 1.349925035939497, "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": 25.568181818181817, "min": 3.3636363636363638, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 148.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.3636363636363638, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 148.0, "max": 1388.0, "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": "1681282761", "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": "1681283235" }, "total": 473.87020288599996, "count": 1, "self": 0.3912281559999542, "children": { "run_training.setup": { "total": 0.1796228330000531, "count": 1, "self": 0.1796228330000531 }, "TrainerController.start_learning": { "total": 473.29935189699995, "count": 1, "self": 0.541009205003661, "children": { "TrainerController._reset_env": { "total": 4.626845083000035, "count": 1, "self": 4.626845083000035 }, "TrainerController.advance": { "total": 468.0029975389963, "count": 18203, "self": 0.27861271699634926, "children": { "env_step": { "total": 467.72438482199993, "count": 18203, "self": 342.2710078870146, "children": { "SubprocessEnvManager._take_step": { "total": 125.17444281798754, "count": 18203, "self": 1.8826275690004763, "children": { "TorchPolicy.evaluate": { "total": 123.29181524898706, "count": 18203, "self": 123.29181524898706 } } }, "workers": { "total": 0.2789341169977888, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 471.77518167298945, "count": 18203, "is_parallel": true, "self": 216.20012973700005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008054079999965325, "count": 1, "is_parallel": true, "self": 0.005734488999905807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023195910000595177, "count": 10, "is_parallel": true, "self": 0.0023195910000595177 } } }, "UnityEnvironment.step": { "total": 0.03727456600000778, "count": 1, "is_parallel": true, "self": 0.0005696799999554969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040595199999415854, "count": 1, "is_parallel": true, "self": 0.00040595199999415854 }, "communicator.exchange": { "total": 0.034467875000018466, "count": 1, "is_parallel": true, "self": 0.034467875000018466 }, "steps_from_proto": { "total": 0.0018310590000396587, "count": 1, "is_parallel": true, "self": 0.00038414000005104754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014469189999886112, "count": 10, "is_parallel": true, "self": 0.0014469189999886112 } } } } } } }, "UnityEnvironment.step": { "total": 255.5750519359894, "count": 18202, "is_parallel": true, "self": 10.085235070992098, "children": { "UnityEnvironment._generate_step_input": { "total": 5.373034258991538, "count": 18202, "is_parallel": true, "self": 5.373034258991538 }, "communicator.exchange": { "total": 208.0655365480012, "count": 18202, "is_parallel": true, "self": 208.0655365480012 }, "steps_from_proto": { "total": 32.05124605800455, "count": 18202, "is_parallel": true, "self": 6.442103781000412, "children": { "_process_rank_one_or_two_observation": { "total": 25.60914227700414, "count": 182020, "is_parallel": true, "self": 25.60914227700414 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.954600000128266e-05, "count": 1, "self": 9.954600000128266e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.19288856303723, "count": 432734, "is_parallel": true, "self": 10.96239900201573, "children": { "process_trajectory": { "total": 257.56200999702133, "count": 432734, "is_parallel": true, "self": 255.86798799902135, "children": { "RLTrainer._checkpoint": { "total": 1.6940219979999824, "count": 4, "is_parallel": true, "self": 1.6940219979999824 } } }, "_update_policy": { "total": 195.66847956400017, "count": 90, "is_parallel": true, "self": 70.20966253400047, "children": { "TorchPPOOptimizer.update": { "total": 125.4588170299997, "count": 4584, "is_parallel": true, "self": 125.4588170299997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12840052399997148, "count": 1, "self": 0.0009959530000287486, "children": { "RLTrainer._checkpoint": { "total": 0.12740457099994273, "count": 1, "self": 0.12740457099994273 } } } } } } }