{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.066491961479187, "min": 1.066491961479187, "max": 2.8715858459472656, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10194.5966796875, "min": 10194.5966796875, "max": 29565.84765625, "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": 12.626968383789062, "min": 0.3503405749797821, "max": 12.626968383789062, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2462.2587890625, "min": 67.96607208251953, "max": 2524.277587890625, "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": 0.06641174172731482, "min": 0.06395448940109454, "max": 0.07708539545084184, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26564696690925926, "min": 0.25581795760437814, "max": 0.35854434262214724, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21335373577826164, "min": 0.12322515858264238, "max": 0.2696587530275186, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8534149431130466, "min": 0.4929006343305695, "max": 1.3023466622712563, "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": 25.454545454545453, "min": 3.272727272727273, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 144.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.272727272727273, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 144.0, "max": 1367.0, "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": "1681032295", "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": "1681032750" }, "total": 455.07698081800004, "count": 1, "self": 0.4323069400000463, "children": { "run_training.setup": { "total": 0.12383485499998415, "count": 1, "self": 0.12383485499998415 }, "TrainerController.start_learning": { "total": 454.520839023, "count": 1, "self": 0.5287755209935767, "children": { "TrainerController._reset_env": { "total": 3.9718877859999964, "count": 1, "self": 3.9718877859999964 }, "TrainerController.advance": { "total": 449.88654754500647, "count": 18204, "self": 0.25918321700368097, "children": { "env_step": { "total": 449.6273643280028, "count": 18204, "self": 325.421841471001, "children": { "SubprocessEnvManager._take_step": { "total": 123.95550185799883, "count": 18204, "self": 1.6915034809955785, "children": { "TorchPolicy.evaluate": { "total": 122.26399837700325, "count": 18204, "self": 122.26399837700325 } } }, "workers": { "total": 0.2500209990029134, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 452.9947308500002, "count": 18204, "is_parallel": true, "self": 210.55272940200092, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00607531299999664, "count": 1, "is_parallel": true, "self": 0.004365672999966819, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017096400000298217, "count": 10, "is_parallel": true, "self": 0.0017096400000298217 } } }, "UnityEnvironment.step": { "total": 0.03612994100001288, "count": 1, "is_parallel": true, "self": 0.0005772659999649932, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036934100000962644, "count": 1, "is_parallel": true, "self": 0.00036934100000962644 }, "communicator.exchange": { "total": 0.033328488000023526, "count": 1, "is_parallel": true, "self": 0.033328488000023526 }, "steps_from_proto": { "total": 0.0018548460000147315, "count": 1, "is_parallel": true, "self": 0.00038945700001136174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014653890000033698, "count": 10, "is_parallel": true, "self": 0.0014653890000033698 } } } } } } }, "UnityEnvironment.step": { "total": 242.4420014479993, "count": 18203, "is_parallel": true, "self": 10.011070659998552, "children": { "UnityEnvironment._generate_step_input": { "total": 5.560107497001383, "count": 18203, "is_parallel": true, "self": 5.560107497001383 }, "communicator.exchange": { "total": 195.5791879880017, "count": 18203, "is_parallel": true, "self": 195.5791879880017 }, "steps_from_proto": { "total": 31.291635302997662, "count": 18203, "is_parallel": true, "self": 6.175258615987502, "children": { "_process_rank_one_or_two_observation": { "total": 25.11637668701016, "count": 182030, "is_parallel": true, "self": 25.11637668701016 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013316799993390305, "count": 1, "self": 0.00013316799993390305, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.31764630102055, "count": 404038, "is_parallel": true, "self": 10.0761888770258, "children": { "process_trajectory": { "total": 245.87296133499453, "count": 404038, "is_parallel": true, "self": 244.27652507499457, "children": { "RLTrainer._checkpoint": { "total": 1.5964362599999617, "count": 4, "is_parallel": true, "self": 1.5964362599999617 } } }, "_update_policy": { "total": 190.36849608900022, "count": 90, "is_parallel": true, "self": 69.14215313299812, "children": { "TorchPPOOptimizer.update": { "total": 121.2263429560021, "count": 4584, "is_parallel": true, "self": 121.2263429560021 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13349500300000727, "count": 1, "self": 0.0008962030000247978, "children": { "RLTrainer._checkpoint": { "total": 0.13259879999998248, "count": 1, "self": 0.13259879999998248 } } } } } } }