{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0040364265441895, "min": 1.0040364265441895, "max": 2.873852252960205, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9608.62890625, "min": 9608.62890625, "max": 29525.958984375, "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": 12.970771789550781, "min": 0.41777828335762024, "max": 12.970771789550781, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.300537109375, "min": 81.04898834228516, "max": 2623.816162109375, "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": 0.07090346473206392, "min": 0.06335814067929545, "max": 0.0772896319446171, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2836138589282557, "min": 0.2617088884478161, "max": 0.36295459813646075, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20142017549597746, "min": 0.11772417878462732, "max": 0.27004651557288917, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8056807019839098, "min": 0.4708967151385093, "max": 1.330227179854524, "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": 25.363636363636363, "min": 3.522727272727273, "max": 25.4, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 155.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.522727272727273, "max": 25.4, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 155.0, "max": 1397.0, "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": "1686224318", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1686224794" }, "total": 475.752323716, "count": 1, "self": 0.3883808379999891, "children": { "run_training.setup": { "total": 0.05853340399994522, "count": 1, "self": 0.05853340399994522 }, "TrainerController.start_learning": { "total": 475.30540947400004, "count": 1, "self": 0.5279360380005755, "children": { "TrainerController._reset_env": { "total": 4.948084498999947, "count": 1, "self": 4.948084498999947 }, "TrainerController.advance": { "total": 469.6817250499996, "count": 18205, "self": 0.258410945011633, "children": { "env_step": { "total": 469.423314104988, "count": 18205, "self": 339.96352761299227, "children": { "SubprocessEnvManager._take_step": { "total": 129.19253908799158, "count": 18205, "self": 1.7888844660100176, "children": { "TorchPolicy.evaluate": { "total": 127.40365462198156, "count": 18205, "self": 127.40365462198156 } } }, "workers": { "total": 0.26724740400413793, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 473.6543426510036, "count": 18205, "is_parallel": true, "self": 225.06619634500942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007000381000011657, "count": 1, "is_parallel": true, "self": 0.00479913900005613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022012419999555277, "count": 10, "is_parallel": true, "self": 0.0022012419999555277 } } }, "UnityEnvironment.step": { "total": 0.03559941899993646, "count": 1, "is_parallel": true, "self": 0.0005572110000002795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000367146000030516, "count": 1, "is_parallel": true, "self": 0.000367146000030516 }, "communicator.exchange": { "total": 0.032604382999920745, "count": 1, "is_parallel": true, "self": 0.032604382999920745 }, "steps_from_proto": { "total": 0.0020706789999849207, "count": 1, "is_parallel": true, "self": 0.000381902000071932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016887769999129887, "count": 10, "is_parallel": true, "self": 0.0016887769999129887 } } } } } } }, "UnityEnvironment.step": { "total": 248.5881463059942, "count": 18204, "is_parallel": true, "self": 9.902435393983751, "children": { "UnityEnvironment._generate_step_input": { "total": 5.556366875003391, "count": 18204, "is_parallel": true, "self": 5.556366875003391 }, "communicator.exchange": { "total": 197.82954818399935, "count": 18204, "is_parallel": true, "self": 197.82954818399935 }, "steps_from_proto": { "total": 35.29979585300771, "count": 18204, "is_parallel": true, "self": 6.747565265978665, "children": { "_process_rank_one_or_two_observation": { "total": 28.552230587029044, "count": 182040, "is_parallel": true, "self": 28.552230587029044 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013384299995777837, "count": 1, "self": 0.00013384299995777837, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.94934846901333, "count": 456224, "is_parallel": true, "self": 10.11275479399319, "children": { "process_trajectory": { "total": 255.17225393402032, "count": 456224, "is_parallel": true, "self": 254.35860160202037, "children": { "RLTrainer._checkpoint": { "total": 0.8136523319999469, "count": 4, "is_parallel": true, "self": 0.8136523319999469 } } }, "_update_policy": { "total": 200.66433974099982, "count": 90, "is_parallel": true, "self": 77.77026033400296, "children": { "TorchPPOOptimizer.update": { "total": 122.89407940699687, "count": 4587, "is_parallel": true, "self": 122.89407940699687 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14753004399995007, "count": 1, "self": 0.0009672139999565843, "children": { "RLTrainer._checkpoint": { "total": 0.14656282999999348, "count": 1, "self": 0.14656282999999348 } } } } } } }