{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9419757127761841, "min": 0.9419757127761841, "max": 2.869649648666382, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9004.345703125, "min": 9004.345703125, "max": 29388.08203125, "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": 12.902280807495117, "min": 0.5042588710784912, "max": 12.902280807495117, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.94482421875, "min": 97.82621765136719, "max": 2613.9814453125, "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": 0.06976628952115253, "min": 0.06383558620348363, "max": 0.07559147855756558, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27906515808461013, "min": 0.25534234481393453, "max": 0.3749828804449827, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20188864327821077, "min": 0.12252479352458728, "max": 0.29505804075914266, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8075545731128431, "min": 0.49009917409834913, "max": 1.4752902037957134, "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": 25.477272727272727, "min": 3.25, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 143.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.25, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 143.0, "max": 1400.0, "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": "1716476415", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716476865" }, "total": 450.192006291, "count": 1, "self": 0.4380499689998487, "children": { "run_training.setup": { "total": 0.0701627160000271, "count": 1, "self": 0.0701627160000271 }, "TrainerController.start_learning": { "total": 449.6837936060001, "count": 1, "self": 0.564143087999696, "children": { "TrainerController._reset_env": { "total": 2.9617433859999664, "count": 1, "self": 2.9617433859999664 }, "TrainerController.advance": { "total": 446.0682478040003, "count": 18201, "self": 0.26590552800246314, "children": { "env_step": { "total": 445.80234227599783, "count": 18201, "self": 291.57777920198873, "children": { "SubprocessEnvManager._take_step": { "total": 153.93919700800564, "count": 18201, "self": 1.4421813479984849, "children": { "TorchPolicy.evaluate": { "total": 152.49701566000715, "count": 18201, "self": 152.49701566000715 } } }, "workers": { "total": 0.28536606600346204, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 448.5580487649911, "count": 18201, "is_parallel": true, "self": 224.25597900098808, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005412032000094769, "count": 1, "is_parallel": true, "self": 0.0037553270002490535, "children": { "_process_rank_one_or_two_observation": { "total": 0.001656704999845715, "count": 10, "is_parallel": true, "self": 0.001656704999845715 } } }, "UnityEnvironment.step": { "total": 0.039203783999937514, "count": 1, "is_parallel": true, "self": 0.0007398179999427157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003689829999302674, "count": 1, "is_parallel": true, "self": 0.0003689829999302674 }, "communicator.exchange": { "total": 0.03622013799997603, "count": 1, "is_parallel": true, "self": 0.03622013799997603 }, "steps_from_proto": { "total": 0.0018748450000884986, "count": 1, "is_parallel": true, "self": 0.0003589460001194311, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015158989999690675, "count": 10, "is_parallel": true, "self": 0.0015158989999690675 } } } } } } }, "UnityEnvironment.step": { "total": 224.30206976400302, "count": 18200, "is_parallel": true, "self": 10.108996865024892, "children": { "UnityEnvironment._generate_step_input": { "total": 5.250770465993355, "count": 18200, "is_parallel": true, "self": 5.250770465993355 }, "communicator.exchange": { "total": 175.8947774169951, "count": 18200, "is_parallel": true, "self": 175.8947774169951 }, "steps_from_proto": { "total": 33.04752501598966, "count": 18200, "is_parallel": true, "self": 6.2365007439999545, "children": { "_process_rank_one_or_two_observation": { "total": 26.81102427198971, "count": 182000, "is_parallel": true, "self": 26.81102427198971 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013466800010064617, "count": 1, "self": 0.00013466800010064617, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.7813452250358, "count": 658315, "is_parallel": true, "self": 13.601161236074063, "children": { "process_trajectory": { "total": 244.00463167396208, "count": 658315, "is_parallel": true, "self": 243.3392510999622, "children": { "RLTrainer._checkpoint": { "total": 0.6653805739998688, "count": 4, "is_parallel": true, "self": 0.6653805739998688 } } }, "_update_policy": { "total": 183.17555231499966, "count": 90, "is_parallel": true, "self": 56.79061363900007, "children": { "TorchPPOOptimizer.update": { "total": 126.38493867599959, "count": 4587, "is_parallel": true, "self": 126.38493867599959 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08952466000005188, "count": 1, "self": 0.0009241230000043288, "children": { "RLTrainer._checkpoint": { "total": 0.08860053700004755, "count": 1, "self": 0.08860053700004755 } } } } } } }