{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.007043719291687, "min": 1.007043719291687, "max": 2.8241264820098877, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 19950.54296875, "min": 19950.54296875, "max": 58061.21875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.779603004455566, "min": 0.7760357856750488, "max": 12.779603004455566, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5099.0615234375, "min": 309.6382751464844, "max": 5099.0615234375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 19701.0, "min": 19701.0, "max": 19701.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06848756776170908, "min": 0.06504460086671514, "max": 0.07002793767685168, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.6163881098553817, "min": 0.5854014078004363, "max": 0.6302514390916651, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20646086452054044, "min": 0.1473869988567973, "max": 0.25762841650863094, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.8581477806848639, "min": 1.3264829897111756, "max": 2.3186557485776786, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6332094556000002e-05, "min": 1.6332094556000002e-05, "max": 0.00028363200545599993, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.000146988851004, "min": 0.000146988851004, "max": 0.0025526880491039995, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10544400000000001, "min": 0.10544400000000001, "max": 0.19454400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9489960000000001, "min": 0.9489960000000001, "max": 1.7508960000000002, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00028165560000000005, "min": 0.00028165560000000005, "max": 0.0047277456, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0025349004000000007, "min": 0.0025349004000000007, "max": 0.0425497104, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 4.373737373737374, "max": 25.454545454545453, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 2520.0, "min": 433.0, "max": 2520.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 4.373737373737374, "max": 25.454545454545453, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 2520.0, "min": 433.0, "max": 2520.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713566864", "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/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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713567343" }, "total": 478.7421149160002, "count": 1, "self": 0.49107300200012105, "children": { "run_training.setup": { "total": 0.057646538999961194, "count": 1, "self": 0.057646538999961194 }, "TrainerController.start_learning": { "total": 478.19339537500014, "count": 1, "self": 0.6061839960361795, "children": { "TrainerController._reset_env": { "total": 3.094463612000027, "count": 1, "self": 3.094463612000027 }, "TrainerController.advance": { "total": 474.3926028959645, "count": 18200, "self": 0.3140445619726506, "children": { "env_step": { "total": 474.07855833399185, "count": 18200, "self": 309.1306409370036, "children": { "SubprocessEnvManager._take_step": { "total": 164.638537814983, "count": 18200, "self": 1.557469046988217, "children": { "TorchPolicy.evaluate": { "total": 163.0810687679948, "count": 18200, "self": 163.0810687679948 } } }, "workers": { "total": 0.3093795820052492, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 476.9153159819941, "count": 18200, "is_parallel": true, "self": 239.57326216697606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005070509000006496, "count": 1, "is_parallel": true, "self": 0.0034863959997437632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015841130002627324, "count": 10, "is_parallel": true, "self": 0.0015841130002627324 } } }, "UnityEnvironment.step": { "total": 0.041315922000194405, "count": 1, "is_parallel": true, "self": 0.00074617100017349, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000458515999980591, "count": 1, "is_parallel": true, "self": 0.000458515999980591 }, "communicator.exchange": { "total": 0.037890329999981986, "count": 1, "is_parallel": true, "self": 0.037890329999981986 }, "steps_from_proto": { "total": 0.0022209050000583375, "count": 1, "is_parallel": true, "self": 0.00043999099943903275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017809140006193047, "count": 10, "is_parallel": true, "self": 0.0017809140006193047 } } } } } } }, "UnityEnvironment.step": { "total": 237.34205381501806, "count": 18199, "is_parallel": true, "self": 10.828303627019068, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8730649880133114, "count": 18199, "is_parallel": true, "self": 5.8730649880133114 }, "communicator.exchange": { "total": 184.27030450799634, "count": 18199, "is_parallel": true, "self": 184.27030450799634 }, "steps_from_proto": { "total": 36.37038069198934, "count": 18199, "is_parallel": true, "self": 7.004594023022264, "children": { "_process_rank_one_or_two_observation": { "total": 29.365786668967075, "count": 181990, "is_parallel": true, "self": 29.365786668967075 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.126499970880104e-05, "count": 1, "self": 4.126499970880104e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 468.3086443030202, "count": 704886, "is_parallel": true, "self": 15.451406292857882, "children": { "process_trajectory": { "total": 258.84102361916257, "count": 704886, "is_parallel": true, "self": 257.90387886416215, "children": { "RLTrainer._checkpoint": { "total": 0.9371447550004177, "count": 4, "is_parallel": true, "self": 0.9371447550004177 } } }, "_update_policy": { "total": 194.01621439099972, "count": 90, "is_parallel": true, "self": 56.92369358899987, "children": { "TorchPPOOptimizer.update": { "total": 137.09252080199985, "count": 4587, "is_parallel": true, "self": 137.09252080199985 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10010360599972046, "count": 1, "self": 0.0009631799994167523, "children": { "RLTrainer._checkpoint": { "total": 0.0991404260003037, "count": 1, "self": 0.0991404260003037 } } } } } } }