{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1253395080566406, "min": 1.1253395080566406, "max": 2.8553688526153564, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10757.1201171875, "min": 10757.1201171875, "max": 29273.2421875, "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": 12.477736473083496, "min": 0.2499975860118866, "max": 12.477736473083496, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2433.15869140625, "min": 48.49953079223633, "max": 2474.44873046875, "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": 0.07024764461679225, "min": 0.06288908286061247, "max": 0.07790245055437874, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.280990578467169, "min": 0.2515563314424499, "max": 0.3524536319315552, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20551214148016536, "min": 0.12727441169394582, "max": 0.2842838919776327, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8220485659206614, "min": 0.5090976467757833, "max": 1.3896173516324923, "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": 25.40909090909091, "min": 3.659090909090909, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 161.0, "max": 1343.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.659090909090909, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 161.0, "max": 1343.0, "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": "1686336328", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1686336822" }, "total": 493.427812571, "count": 1, "self": 0.43634634799980176, "children": { "run_training.setup": { "total": 0.04200764700010495, "count": 1, "self": 0.04200764700010495 }, "TrainerController.start_learning": { "total": 492.9494585760001, "count": 1, "self": 0.5703240519970905, "children": { "TrainerController._reset_env": { "total": 5.097235103999992, "count": 1, "self": 5.097235103999992 }, "TrainerController.advance": { "total": 487.13274540700274, "count": 18201, "self": 0.28484980900191204, "children": { "env_step": { "total": 486.84789559800083, "count": 18201, "self": 354.23974151797665, "children": { "SubprocessEnvManager._take_step": { "total": 132.3351141610117, "count": 18201, "self": 1.8474283310210922, "children": { "TorchPolicy.evaluate": { "total": 130.4876858299906, "count": 18201, "self": 130.4876858299906 } } }, "workers": { "total": 0.2730399190124899, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 491.3652197659816, "count": 18201, "is_parallel": true, "self": 233.14530456498676, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005915068000035717, "count": 1, "is_parallel": true, "self": 0.004095336999967003, "children": { "_process_rank_one_or_two_observation": { "total": 0.001819731000068714, "count": 10, "is_parallel": true, "self": 0.001819731000068714 } } }, "UnityEnvironment.step": { "total": 0.07643424999992021, "count": 1, "is_parallel": true, "self": 0.0006721619998870665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048262600000725797, "count": 1, "is_parallel": true, "self": 0.00048262600000725797 }, "communicator.exchange": { "total": 0.07268228700002055, "count": 1, "is_parallel": true, "self": 0.07268228700002055 }, "steps_from_proto": { "total": 0.002597175000005336, "count": 1, "is_parallel": true, "self": 0.0004339030001574429, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021632719998478933, "count": 10, "is_parallel": true, "self": 0.0021632719998478933 } } } } } } }, "UnityEnvironment.step": { "total": 258.2199152009948, "count": 18200, "is_parallel": true, "self": 10.506353037976737, "children": { "UnityEnvironment._generate_step_input": { "total": 5.597870025004568, "count": 18200, "is_parallel": true, "self": 5.597870025004568 }, "communicator.exchange": { "total": 204.84560094199173, "count": 18200, "is_parallel": true, "self": 204.84560094199173 }, "steps_from_proto": { "total": 37.27009119602178, "count": 18200, "is_parallel": true, "self": 6.74227787603138, "children": { "_process_rank_one_or_two_observation": { "total": 30.5278133199904, "count": 182000, "is_parallel": true, "self": 30.5278133199904 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013748600008511858, "count": 1, "self": 0.00013748600008511858, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.0222723390042, "count": 459547, "is_parallel": true, "self": 10.630487766996339, "children": { "process_trajectory": { "total": 265.8177518540083, "count": 459547, "is_parallel": true, "self": 264.8782922480084, "children": { "RLTrainer._checkpoint": { "total": 0.9394596059999003, "count": 4, "is_parallel": true, "self": 0.9394596059999003 } } }, "_update_policy": { "total": 206.57403271799956, "count": 90, "is_parallel": true, "self": 81.7820542120055, "children": { "TorchPPOOptimizer.update": { "total": 124.79197850599405, "count": 4587, "is_parallel": true, "self": 124.79197850599405 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1490165270001853, "count": 1, "self": 0.0011655190003239113, "children": { "RLTrainer._checkpoint": { "total": 0.1478510079998614, "count": 1, "self": 0.1478510079998614 } } } } } } }