{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9993101954460144, "min": 0.9993101954460144, "max": 2.866244316101074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9563.3984375, "min": 9563.3984375, "max": 29416.265625, "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": 12.576066970825195, "min": 0.27747318148612976, "max": 12.576066970825195, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2452.3330078125, "min": 53.82979965209961, "max": 2550.501953125, "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": 0.07345555118780454, "min": 0.06034702958776524, "max": 0.07458168667485462, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2938222047512182, "min": 0.25231527956316757, "max": 0.37290843337427315, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1992142649330929, "min": 0.11732224045965055, "max": 0.30621126919400454, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7968570597323716, "min": 0.4692889618386022, "max": 1.5310563459700228, "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": 24.931818181818183, "min": 2.8863636363636362, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 127.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 2.8863636363636362, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 127.0, "max": 1381.0, "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": "1680443550", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/mnt/slurm-home/h_kambe/miniconda3/envs/py39-deep-rl-class/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1680443756" }, "total": 206.35802875366062, "count": 1, "self": 0.32059095706790686, "children": { "run_training.setup": { "total": 0.05711450334638357, "count": 1, "self": 0.05711450334638357 }, "TrainerController.start_learning": { "total": 205.98032329324633, "count": 1, "self": 0.2908992441371083, "children": { "TrainerController._reset_env": { "total": 9.076232192106545, "count": 1, "self": 9.076232192106545 }, "TrainerController.advance": { "total": 196.45816499460489, "count": 18208, "self": 0.15620674844831228, "children": { "env_step": { "total": 196.30195824615657, "count": 18208, "self": 128.4781814245507, "children": { "SubprocessEnvManager._take_step": { "total": 67.68129522632807, "count": 18208, "self": 0.8802304044365883, "children": { "TorchPolicy.evaluate": { "total": 66.80106482189149, "count": 18208, "self": 66.80106482189149 } } }, "workers": { "total": 0.14248159527778625, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 205.5498168328777, "count": 18208, "is_parallel": true, "self": 117.13109902944416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010628467425704002, "count": 1, "is_parallel": true, "self": 0.00029126182198524475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007715849205851555, "count": 10, "is_parallel": true, "self": 0.0007715849205851555 } } }, "UnityEnvironment.step": { "total": 0.020847042091190815, "count": 1, "is_parallel": true, "self": 0.00025931745767593384, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008026650175452232, "count": 1, "is_parallel": true, "self": 0.0008026650175452232 }, "communicator.exchange": { "total": 0.019063190557062626, "count": 1, "is_parallel": true, "self": 0.019063190557062626 }, "steps_from_proto": { "total": 0.000721869058907032, "count": 1, "is_parallel": true, "self": 0.00016753468662500381, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005543343722820282, "count": 10, "is_parallel": true, "self": 0.0005543343722820282 } } } } } } }, "UnityEnvironment.step": { "total": 88.41871780343354, "count": 18207, "is_parallel": true, "self": 3.683372021652758, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2040326464921236, "count": 18207, "is_parallel": true, "self": 2.2040326464921236 }, "communicator.exchange": { "total": 69.78663670737296, "count": 18207, "is_parallel": true, "self": 69.78663670737296 }, "steps_from_proto": { "total": 12.744676427915692, "count": 18207, "is_parallel": true, "self": 2.797866209410131, "children": { "_process_rank_one_or_two_observation": { "total": 9.946810218505561, "count": 182070, "is_parallel": true, "self": 9.946810218505561 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.832461804151535e-05, "count": 1, "self": 6.832461804151535e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 196.30190872680396, "count": 126072, "is_parallel": true, "self": 1.0359489414840937, "children": { "process_trajectory": { "total": 105.1361311962828, "count": 126072, "is_parallel": true, "self": 104.29716876335442, "children": { "RLTrainer._checkpoint": { "total": 0.8389624329283834, "count": 4, "is_parallel": true, "self": 0.8389624329283834 } } }, "_update_policy": { "total": 90.12982858903706, "count": 90, "is_parallel": true, "self": 27.997073888778687, "children": { "TorchPPOOptimizer.update": { "total": 62.132754700258374, "count": 4587, "is_parallel": true, "self": 62.132754700258374 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15495853777974844, "count": 1, "self": 0.005292384885251522, "children": { "RLTrainer._checkpoint": { "total": 0.14966615289449692, "count": 1, "self": 0.14966615289449692 } } } } } } }