{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.055451512336731, "min": 1.055451512336731, "max": 2.867302656173706, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10089.0615234375, "min": 10089.0615234375, "max": 29364.046875, "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": 12.630255699157715, "min": 0.37473225593566895, "max": 12.630255699157715, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2462.89990234375, "min": 72.69805908203125, "max": 2534.5458984375, "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": 0.07089697661057488, "min": 0.06155606434200023, "max": 0.07594182110749934, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28358790644229953, "min": 0.2462242573680009, "max": 0.37970910553749665, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20045469679376657, "min": 0.11664071251574319, "max": 0.2900810149662635, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8018187871750663, "min": 0.46656285006297277, "max": 1.4299725510326087, "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": 25.5, "min": 3.2954545454545454, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 145.0, "max": 1352.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.2954545454545454, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 145.0, "max": 1352.0, "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": "1704603942", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704604411" }, "total": 469.210015548, "count": 1, "self": 0.49232972999982394, "children": { "run_training.setup": { "total": 0.050948766000033174, "count": 1, "self": 0.050948766000033174 }, "TrainerController.start_learning": { "total": 468.66673705200014, "count": 1, "self": 0.6009158229993545, "children": { "TrainerController._reset_env": { "total": 3.096576672000083, "count": 1, "self": 3.096576672000083 }, "TrainerController.advance": { "total": 464.86970745100086, "count": 18200, "self": 0.28776632000074187, "children": { "env_step": { "total": 464.5819411310001, "count": 18200, "self": 306.9815451479824, "children": { "SubprocessEnvManager._take_step": { "total": 157.29733758002055, "count": 18200, "self": 1.5416031310237486, "children": { "TorchPolicy.evaluate": { "total": 155.7557344489968, "count": 18200, "self": 155.7557344489968 } } }, "workers": { "total": 0.30305840299718056, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 467.38201580499936, "count": 18200, "is_parallel": true, "self": 229.65665746498996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00543816100002914, "count": 1, "is_parallel": true, "self": 0.0033157620000565657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021223989999725745, "count": 10, "is_parallel": true, "self": 0.0021223989999725745 } } }, "UnityEnvironment.step": { "total": 0.04150479700001597, "count": 1, "is_parallel": true, "self": 0.0006752360000064073, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005172840000113865, "count": 1, "is_parallel": true, "self": 0.0005172840000113865 }, "communicator.exchange": { "total": 0.03832216000000699, "count": 1, "is_parallel": true, "self": 0.03832216000000699 }, "steps_from_proto": { "total": 0.001990116999991187, "count": 1, "is_parallel": true, "self": 0.00042315000007420167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015669669999169855, "count": 10, "is_parallel": true, "self": 0.0015669669999169855 } } } } } } }, "UnityEnvironment.step": { "total": 237.7253583400094, "count": 18199, "is_parallel": true, "self": 11.12182515399354, "children": { "UnityEnvironment._generate_step_input": { "total": 5.731163699007652, "count": 18199, "is_parallel": true, "self": 5.731163699007652 }, "communicator.exchange": { "total": 184.87950279200174, "count": 18199, "is_parallel": true, "self": 184.87950279200174 }, "steps_from_proto": { "total": 35.992866695006455, "count": 18199, "is_parallel": true, "self": 6.709548436988939, "children": { "_process_rank_one_or_two_observation": { "total": 29.283318258017516, "count": 181990, "is_parallel": true, "self": 29.283318258017516 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016788499988251715, "count": 1, "self": 0.00016788499988251715, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 459.0446566000501, "count": 690866, "is_parallel": true, "self": 14.932108807123313, "children": { "process_trajectory": { "total": 253.88687899792728, "count": 690866, "is_parallel": true, "self": 253.02472981492724, "children": { "RLTrainer._checkpoint": { "total": 0.8621491830000423, "count": 4, "is_parallel": true, "self": 0.8621491830000423 } } }, "_update_policy": { "total": 190.22566879499948, "count": 90, "is_parallel": true, "self": 61.26042637000319, "children": { "TorchPPOOptimizer.update": { "total": 128.9652424249963, "count": 4584, "is_parallel": true, "self": 128.9652424249963 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09936922099996082, "count": 1, "self": 0.0010925769997811585, "children": { "RLTrainer._checkpoint": { "total": 0.09827664400017966, "count": 1, "self": 0.09827664400017966 } } } } } } }