{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8465259075164795, "min": 2.8465259075164795, "max": 2.8840198516845703, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29370.453125, "min": 29370.453125, "max": 29535.24609375, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.0698727369308472, "min": 0.2647106349468231, "max": 1.0698727369308472, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 219.32391357421875, "min": 51.35386276245117, "max": 219.32391357421875, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07101536299302881, "min": 0.07101536299302881, "max": 0.0756757696731167, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35507681496514404, "min": 0.3027030786924668, "max": 0.35507681496514404, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16877585576445447, "min": 0.08650330294325363, "max": 0.16877585576445447, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8438792788222724, "min": 0.34601321177301453, "max": 0.8438792788222724, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 4.818181818181818, "min": 2.6363636363636362, "max": 4.818181818181818, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 265.0, "min": 116.0, "max": 265.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 4.818181818181818, "min": 2.6363636363636362, "max": 4.818181818181818, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 265.0, "min": 116.0, "max": 265.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710323263", "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": "1710323316" }, "total": 52.65013245099999, "count": 1, "self": 0.38810150499989504, "children": { "run_training.setup": { "total": 0.054268577000016194, "count": 1, "self": 0.054268577000016194 }, "TrainerController.start_learning": { "total": 52.20776236900008, "count": 1, "self": 0.08572446299922376, "children": { "TrainerController._reset_env": { "total": 2.7581361119999883, "count": 1, "self": 2.7581361119999883 }, "TrainerController.advance": { "total": 49.26768187800087, "count": 1873, "self": 0.03305610400286696, "children": { "env_step": { "total": 49.234625773998005, "count": 1873, "self": 31.44155397699751, "children": { "SubprocessEnvManager._take_step": { "total": 17.762227375001203, "count": 1873, "self": 0.16356779400280175, "children": { "TorchPolicy.evaluate": { "total": 17.5986595809984, "count": 1873, "self": 17.5986595809984 } } }, "workers": { "total": 0.030844421999290716, "count": 1873, "self": 0.0, "children": { "worker_root": { "total": 51.984810334996496, "count": 1873, "is_parallel": true, "self": 27.61829472799684, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005644970000048488, "count": 1, "is_parallel": true, "self": 0.004002634000130456, "children": { "_process_rank_one_or_two_observation": { "total": 0.001642335999918032, "count": 10, "is_parallel": true, "self": 0.001642335999918032 } } }, "UnityEnvironment.step": { "total": 0.038520612999946025, "count": 1, "is_parallel": true, "self": 0.000724676000004365, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005193460000327832, "count": 1, "is_parallel": true, "self": 0.0005193460000327832 }, "communicator.exchange": { "total": 0.03508816599992315, "count": 1, "is_parallel": true, "self": 0.03508816599992315 }, "steps_from_proto": { "total": 0.0021884249999857275, "count": 1, "is_parallel": true, "self": 0.00044674799994481873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017416770000409088, "count": 10, "is_parallel": true, "self": 0.0017416770000409088 } } } } } } }, "UnityEnvironment.step": { "total": 24.366515606999656, "count": 1872, "is_parallel": true, "self": 1.0850845019955386, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5968603589998338, "count": 1872, "is_parallel": true, "self": 0.5968603589998338 }, "communicator.exchange": { "total": 18.832599698003605, "count": 1872, "is_parallel": true, "self": 18.832599698003605 }, "steps_from_proto": { "total": 3.851971048000678, "count": 1872, "is_parallel": true, "self": 0.7416369170100552, "children": { "_process_rank_one_or_two_observation": { "total": 3.1103341309906227, "count": 18720, "is_parallel": true, "self": 3.1103341309906227 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022979900006703247, "count": 1, "self": 0.00022979900006703247, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 48.64733969300585, "count": 74718, "is_parallel": true, "self": 1.6331575600130463, "children": { "process_trajectory": { "total": 27.286226292992865, "count": 74718, "is_parallel": true, "self": 26.762694277992978, "children": { "RLTrainer._checkpoint": { "total": 0.523532014999887, "count": 4, "is_parallel": true, "self": 0.523532014999887 } } }, "_update_policy": { "total": 19.727955839999936, "count": 9, "is_parallel": true, "self": 5.924913302999698, "children": { "TorchPPOOptimizer.update": { "total": 13.803042537000238, "count": 456, "is_parallel": true, "self": 13.803042537000238 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09599011699992843, "count": 1, "self": 0.0009753819999787083, "children": { "RLTrainer._checkpoint": { "total": 0.09501473499994972, "count": 1, "self": 0.09501473499994972 } } } } } } }