{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0503441095352173, "min": 1.0503441095352173, "max": 2.875824451446533, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10074.900390625, "min": 10074.900390625, "max": 29482.951171875, "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": 12.725275039672852, "min": 0.36046087741851807, "max": 12.725275039672852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.4287109375, "min": 69.92941284179688, "max": 2550.26611328125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06852482275109437, "min": 0.060149045447449714, "max": 0.07640664620542106, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27409929100437747, "min": 0.24059618178979886, "max": 0.38203323102710535, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18821870426044746, "min": 0.11004175161303698, "max": 0.26508480216942576, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7528748170417898, "min": 0.4401670064521479, "max": 1.325424010847129, "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": 25.227272727272727, "min": 3.340909090909091, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 147.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.340909090909091, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 147.0, "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": "1692593927", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ml2/anaconda3/envs/huggingface/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": "1692594261" }, "total": 333.8205900809844, "count": 1, "self": 0.268843955011107, "children": { "run_training.setup": { "total": 0.013992929976666346, "count": 1, "self": 0.013992929976666346 }, "TrainerController.start_learning": { "total": 333.53775319599663, "count": 1, "self": 0.44494454335654154, "children": { "TrainerController._reset_env": { "total": 3.2963624989788514, "count": 1, "self": 3.2963624989788514 }, "TrainerController.advance": { "total": 329.6916414886364, "count": 18206, "self": 0.21558574517257512, "children": { "env_step": { "total": 329.4760557434638, "count": 18206, "self": 244.99289268424036, "children": { "SubprocessEnvManager._take_step": { "total": 84.24716137218638, "count": 18206, "self": 1.2630920589435846, "children": { "TorchPolicy.evaluate": { "total": 82.9840693132428, "count": 18206, "self": 82.9840693132428 } } }, "workers": { "total": 0.23600168703706004, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 332.9098785308306, "count": 18206, "is_parallel": true, "self": 162.35756477795076, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013135169865563512, "count": 1, "is_parallel": true, "self": 0.00032741203904151917, "children": { "_process_rank_one_or_two_observation": { "total": 0.000986104947514832, "count": 10, "is_parallel": true, "self": 0.000986104947514832 } } }, "UnityEnvironment.step": { "total": 0.021293447993230075, "count": 1, "is_parallel": true, "self": 0.00025366697809658945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017415298498235643, "count": 1, "is_parallel": true, "self": 0.00017415298498235643 }, "communicator.exchange": { "total": 0.019808052020380273, "count": 1, "is_parallel": true, "self": 0.019808052020380273 }, "steps_from_proto": { "total": 0.0010575760097708553, "count": 1, "is_parallel": true, "self": 0.00020820999634452164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008493660134263337, "count": 10, "is_parallel": true, "self": 0.0008493660134263337 } } } } } } }, "UnityEnvironment.step": { "total": 170.55231375287985, "count": 18205, "is_parallel": true, "self": 9.473233586206334, "children": { "UnityEnvironment._generate_step_input": { "total": 4.391863424185431, "count": 18205, "is_parallel": true, "self": 4.391863424185431 }, "communicator.exchange": { "total": 128.81255618936848, "count": 18205, "is_parallel": true, "self": 128.81255618936848 }, "steps_from_proto": { "total": 27.87466055311961, "count": 18205, "is_parallel": true, "self": 4.421009190817131, "children": { "_process_rank_one_or_two_observation": { "total": 23.45365136230248, "count": 182050, "is_parallel": true, "self": 23.45365136230248 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011900800745934248, "count": 1, "self": 0.00011900800745934248, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 328.9197901933221, "count": 199337, "is_parallel": true, "self": 2.8681928561418317, "children": { "process_trajectory": { "total": 185.59232343907934, "count": 199337, "is_parallel": true, "self": 184.90078791510314, "children": { "RLTrainer._checkpoint": { "total": 0.6915355239761993, "count": 4, "is_parallel": true, "self": 0.6915355239761993 } } }, "_update_policy": { "total": 140.45927389810095, "count": 90, "is_parallel": true, "self": 36.981606579589425, "children": { "TorchPPOOptimizer.update": { "total": 103.47766731851152, "count": 4587, "is_parallel": true, "self": 103.47766731851152 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10468565701739863, "count": 1, "self": 0.0007233440410345793, "children": { "RLTrainer._checkpoint": { "total": 0.10396231297636405, "count": 1, "self": 0.10396231297636405 } } } } } } }