{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9651818871498108, "min": 0.9651818871498108, "max": 2.871211528778076, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9226.173828125, "min": 9226.173828125, "max": 29435.66015625, "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": 13.047371864318848, "min": 0.3412988483905792, "max": 13.047371864318848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.237548828125, "min": 66.21197509765625, "max": 2648.23828125, "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": 0.06630064334960623, "min": 0.06211848271064525, "max": 0.07463830654616649, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2652025733984249, "min": 0.248473930842581, "max": 0.3607979266671464, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19799876804737482, "min": 0.0990501383899291, "max": 0.2778143945862265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7919950721894993, "min": 0.3962005535597164, "max": 1.3890719729311325, "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": 25.59090909090909, "min": 3.0681818181818183, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 135.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.0681818181818183, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 135.0, "max": 1394.0, "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": "1723205688", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723206262" }, "total": 573.1793268340001, "count": 1, "self": 0.5909281540000393, "children": { "run_training.setup": { "total": 0.07234776799998599, "count": 1, "self": 0.07234776799998599 }, "TrainerController.start_learning": { "total": 572.5160509120001, "count": 1, "self": 0.8314927589980243, "children": { "TrainerController._reset_env": { "total": 2.9204430300000013, "count": 1, "self": 2.9204430300000013 }, "TrainerController.advance": { "total": 568.6667390850021, "count": 18202, "self": 0.3995654250156804, "children": { "env_step": { "total": 568.2671736599864, "count": 18202, "self": 439.57505598799423, "children": { "SubprocessEnvManager._take_step": { "total": 128.28103429399494, "count": 18202, "self": 2.2704245319827123, "children": { "TorchPolicy.evaluate": { "total": 126.01060976201222, "count": 18202, "self": 126.01060976201222 } } }, "workers": { "total": 0.4110833779972154, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 570.6352826609866, "count": 18202, "is_parallel": true, "self": 264.7339492039813, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00669938800001546, "count": 1, "is_parallel": true, "self": 0.00451453100015442, "children": { "_process_rank_one_or_two_observation": { "total": 0.00218485699986104, "count": 10, "is_parallel": true, "self": 0.00218485699986104 } } }, "UnityEnvironment.step": { "total": 0.047736191000012695, "count": 1, "is_parallel": true, "self": 0.0007787319999579267, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044407500001852895, "count": 1, "is_parallel": true, "self": 0.00044407500001852895 }, "communicator.exchange": { "total": 0.044220299000016894, "count": 1, "is_parallel": true, "self": 0.044220299000016894 }, "steps_from_proto": { "total": 0.002293085000019346, "count": 1, "is_parallel": true, "self": 0.00042318100008742476, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018699039999319211, "count": 10, "is_parallel": true, "self": 0.0018699039999319211 } } } } } } }, "UnityEnvironment.step": { "total": 305.9013334570053, "count": 18201, "is_parallel": true, "self": 14.610489484008781, "children": { "UnityEnvironment._generate_step_input": { "total": 7.3204186350045575, "count": 18201, "is_parallel": true, "self": 7.3204186350045575 }, "communicator.exchange": { "total": 240.20672068199895, "count": 18201, "is_parallel": true, "self": 240.20672068199895 }, "steps_from_proto": { "total": 43.763704655993024, "count": 18201, "is_parallel": true, "self": 8.613554580976597, "children": { "_process_rank_one_or_two_observation": { "total": 35.15015007501643, "count": 182010, "is_parallel": true, "self": 35.15015007501643 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000693448999982138, "count": 1, "self": 0.000693448999982138, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 561.7924912019633, "count": 772489, "is_parallel": true, "self": 17.19076556787786, "children": { "process_trajectory": { "total": 306.9675214420856, "count": 772489, "is_parallel": true, "self": 306.27018156108545, "children": { "RLTrainer._checkpoint": { "total": 0.6973398810001754, "count": 4, "is_parallel": true, "self": 0.6973398810001754 } } }, "_update_policy": { "total": 237.63420419199986, "count": 90, "is_parallel": true, "self": 71.6655526060016, "children": { "TorchPPOOptimizer.update": { "total": 165.96865158599826, "count": 4587, "is_parallel": true, "self": 165.96865158599826 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09668258900001092, "count": 1, "self": 0.0011919269998088566, "children": { "RLTrainer._checkpoint": { "total": 0.09549066200020206, "count": 1, "self": 0.09549066200020206 } } } } } } }