{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9640780687332153, "min": 0.9640780687332153, "max": 2.8610353469848633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9236.83203125, "min": 9236.83203125, "max": 29331.333984375, "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": 12.780162811279297, "min": 0.4367670714855194, "max": 12.780162811279297, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.1318359375, "min": 84.7328109741211, "max": 2607.12939453125, "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": 0.0650869872444994, "min": 0.06404202807644455, "max": 0.07464493977065158, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2603479489779976, "min": 0.2581159092700474, "max": 0.3701821833314813, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21373774323101138, "min": 0.10709334936851234, "max": 0.32132365405559543, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8549509729240455, "min": 0.42837339747404934, "max": 1.6066182702779772, "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": 2.8863636363636362, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 127.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 2.8863636363636362, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 127.0, "max": 1379.0, "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": "1728550351", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728551008" }, "total": 656.9555333779999, "count": 1, "self": 0.5924226619998763, "children": { "run_training.setup": { "total": 0.08571118800000477, "count": 1, "self": 0.08571118800000477 }, "TrainerController.start_learning": { "total": 656.277399528, "count": 1, "self": 1.0342466840033921, "children": { "TrainerController._reset_env": { "total": 3.35245730500003, "count": 1, "self": 3.35245730500003 }, "TrainerController.advance": { "total": 651.7882609769965, "count": 18204, "self": 0.46141998000848616, "children": { "env_step": { "total": 651.326840996988, "count": 18204, "self": 502.4855227209895, "children": { "SubprocessEnvManager._take_step": { "total": 148.32820747000585, "count": 18204, "self": 2.6520135879908366, "children": { "TorchPolicy.evaluate": { "total": 145.676193882015, "count": 18204, "self": 145.676193882015 } } }, "workers": { "total": 0.5131108059927101, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 654.0229937899953, "count": 18204, "is_parallel": true, "self": 308.2524243249967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031948739999734244, "count": 1, "is_parallel": true, "self": 0.0010088579997500347, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021860160002233897, "count": 10, "is_parallel": true, "self": 0.0021860160002233897 } } }, "UnityEnvironment.step": { "total": 0.0991208010000264, "count": 1, "is_parallel": true, "self": 0.0009044969999649766, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000524965000067823, "count": 1, "is_parallel": true, "self": 0.000524965000067823 }, "communicator.exchange": { "total": 0.09550775100001374, "count": 1, "is_parallel": true, "self": 0.09550775100001374 }, "steps_from_proto": { "total": 0.0021835879999798635, "count": 1, "is_parallel": true, "self": 0.00039415299988831975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017894350000915438, "count": 10, "is_parallel": true, "self": 0.0017894350000915438 } } } } } } }, "UnityEnvironment.step": { "total": 345.77056946499863, "count": 18203, "is_parallel": true, "self": 16.451973516009616, "children": { "UnityEnvironment._generate_step_input": { "total": 8.449030832979133, "count": 18203, "is_parallel": true, "self": 8.449030832979133 }, "communicator.exchange": { "total": 273.42918441199834, "count": 18203, "is_parallel": true, "self": 273.42918441199834 }, "steps_from_proto": { "total": 47.440380704011545, "count": 18203, "is_parallel": true, "self": 9.803344566996088, "children": { "_process_rank_one_or_two_observation": { "total": 37.63703613701546, "count": 182030, "is_parallel": true, "self": 37.63703613701546 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033848300017780275, "count": 1, "self": 0.00033848300017780275, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 644.0305826980419, "count": 882356, "is_parallel": true, "self": 20.448732153957394, "children": { "process_trajectory": { "total": 345.42290523008614, "count": 882356, "is_parallel": true, "self": 344.6596684480862, "children": { "RLTrainer._checkpoint": { "total": 0.7632367819999217, "count": 4, "is_parallel": true, "self": 0.7632367819999217 } } }, "_update_policy": { "total": 278.1589453139984, "count": 90, "is_parallel": true, "self": 84.47585536099848, "children": { "TorchPPOOptimizer.update": { "total": 193.68308995299992, "count": 4587, "is_parallel": true, "self": 193.68308995299992 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10209607899992079, "count": 1, "self": 0.0015449390000412677, "children": { "RLTrainer._checkpoint": { "total": 0.10055113999987952, "count": 1, "self": 0.10055113999987952 } } } } } } }