{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9222192764282227, "min": 0.9188346862792969, "max": 2.861781358718872, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8805.349609375, "min": 8805.349609375, "max": 29307.501953125, "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": 13.031908988952637, "min": 0.16615651547908783, "max": 13.031908988952637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2541.22216796875, "min": 32.2343635559082, "max": 2630.662109375, "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": 0.06854683851855167, "min": 0.061288413583122966, "max": 0.07509013645775506, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2741873540742067, "min": 0.24515365433249187, "max": 0.3754506822887753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19078716657617512, "min": 0.11631495980705664, "max": 0.3018731833526901, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7631486663047005, "min": 0.46525983922822656, "max": 1.3318484960233463, "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": 26.068181818181817, "min": 3.1363636363636362, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 138.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.1363636363636362, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 138.0, "max": 1403.0, "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": "1675504357", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675504778" }, "total": 421.10849042200005, "count": 1, "self": 0.3989811460000965, "children": { "run_training.setup": { "total": 0.10379697999999848, "count": 1, "self": 0.10379697999999848 }, "TrainerController.start_learning": { "total": 420.605712296, "count": 1, "self": 0.5252016510002022, "children": { "TrainerController._reset_env": { "total": 10.178217745000012, "count": 1, "self": 10.178217745000012 }, "TrainerController.advance": { "total": 409.7842470989998, "count": 18201, "self": 0.2643055619986967, "children": { "env_step": { "total": 409.5199415370011, "count": 18201, "self": 266.6593698880027, "children": { "SubprocessEnvManager._take_step": { "total": 142.60995597399688, "count": 18201, "self": 1.3450918279982602, "children": { "TorchPolicy.evaluate": { "total": 141.26486414599862, "count": 18201, "self": 32.414534828995215, "children": { "TorchPolicy.sample_actions": { "total": 108.8503293170034, "count": 18201, "self": 108.8503293170034 } } } } }, "workers": { "total": 0.2506156750015407, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 419.39686518899936, "count": 18201, "is_parallel": true, "self": 203.31221350499948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012037215999981754, "count": 1, "is_parallel": true, "self": 0.004116053999950964, "children": { "_process_rank_one_or_two_observation": { "total": 0.00792116200003079, "count": 10, "is_parallel": true, "self": 0.00792116200003079 } } }, "UnityEnvironment.step": { "total": 0.03994516299999873, "count": 1, "is_parallel": true, "self": 0.0004128890000174579, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002704810000011548, "count": 1, "is_parallel": true, "self": 0.0002704810000011548 }, "communicator.exchange": { "total": 0.037439931999983855, "count": 1, "is_parallel": true, "self": 0.037439931999983855 }, "steps_from_proto": { "total": 0.001821860999996261, "count": 1, "is_parallel": true, "self": 0.0004021809999414927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014196800000547682, "count": 10, "is_parallel": true, "self": 0.0014196800000547682 } } } } } } }, "UnityEnvironment.step": { "total": 216.08465168399988, "count": 18200, "is_parallel": true, "self": 8.188788621994433, "children": { "UnityEnvironment._generate_step_input": { "total": 4.767814175007004, "count": 18200, "is_parallel": true, "self": 4.767814175007004 }, "communicator.exchange": { "total": 171.86768169800308, "count": 18200, "is_parallel": true, "self": 171.86768169800308 }, "steps_from_proto": { "total": 31.26036718899536, "count": 18200, "is_parallel": true, "self": 6.247478481985553, "children": { "_process_rank_one_or_two_observation": { "total": 25.012888707009807, "count": 182000, "is_parallel": true, "self": 25.012888707009807 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.606699999636476e-05, "count": 1, "self": 3.606699999636476e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 406.90625794001767, "count": 339665, "is_parallel": true, "self": 8.965125950020479, "children": { "process_trajectory": { "total": 234.37231652799684, "count": 339665, "is_parallel": true, "self": 233.59184173799687, "children": { "RLTrainer._checkpoint": { "total": 0.7804747899999711, "count": 4, "is_parallel": true, "self": 0.7804747899999711 } } }, "_update_policy": { "total": 163.56881546200032, "count": 90, "is_parallel": true, "self": 40.979415210998354, "children": { "TorchPPOOptimizer.update": { "total": 122.58940025100196, "count": 4587, "is_parallel": true, "self": 122.58940025100196 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11800973399999748, "count": 1, "self": 0.0008516589999771895, "children": { "RLTrainer._checkpoint": { "total": 0.11715807500002029, "count": 1, "self": 0.11715807500002029 } } } } } } }