{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9026374220848083, "min": 0.9026374220848083, "max": 2.8332505226135254, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8578.666015625, "min": 8578.666015625, "max": 28921.8203125, "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": 12.736498832702637, "min": 0.4214533865451813, "max": 12.736498832702637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2483.6171875, "min": 81.76195526123047, "max": 2555.2578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06736686691218376, "min": 0.06243631539024029, "max": 0.06982902386125893, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.269467467648735, "min": 0.24974526156096116, "max": 0.34914511930629466, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19669783531742938, "min": 0.1532199336489772, "max": 0.2714219020277846, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7867913412697175, "min": 0.6128797345959088, "max": 1.357109510138923, "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.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.Environment.CumulativeReward.mean": { "value": 25.681818181818183, "min": 4.159090909090909, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 183.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 4.159090909090909, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 183.0, "max": 1369.0, "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": "1782874888", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/hf_rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1782875423" }, "total": 535.3767337770005, "count": 1, "self": 0.9997001290003027, "children": { "run_training.setup": { "total": 0.08191442499992263, "count": 1, "self": 0.08191442499992263 }, "TrainerController.start_learning": { "total": 534.2951192230003, "count": 1, "self": 0.4432851429864968, "children": { "TrainerController._reset_env": { "total": 9.072256903999914, "count": 1, "self": 9.072256903999914 }, "TrainerController.advance": { "total": 524.5217671980145, "count": 18192, "self": 0.4410181371140425, "children": { "env_step": { "total": 417.32140018092286, "count": 18192, "self": 371.1622646230353, "children": { "SubprocessEnvManager._take_step": { "total": 45.87185612900612, "count": 18192, "self": 1.5182860499953676, "children": { "TorchPolicy.evaluate": { "total": 44.35357007901075, "count": 18192, "self": 44.35357007901075 } } }, "workers": { "total": 0.28727942888144753, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 532.4738194969932, "count": 18192, "is_parallel": true, "self": 196.53359051599637, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002990689999933238, "count": 1, "is_parallel": true, "self": 0.0010561089984548744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019345810014783638, "count": 10, "is_parallel": true, "self": 0.0019345810014783638 } } }, "UnityEnvironment.step": { "total": 0.0442738259998805, "count": 1, "is_parallel": true, "self": 0.00024298100015585078, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002411659997960669, "count": 1, "is_parallel": true, "self": 0.0002411659997960669 }, "communicator.exchange": { "total": 0.042945416000293335, "count": 1, "is_parallel": true, "self": 0.042945416000293335 }, "steps_from_proto": { "total": 0.000844262999635248, "count": 1, "is_parallel": true, "self": 0.00018642900158738485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006578339980478631, "count": 10, "is_parallel": true, "self": 0.0006578339980478631 } } } } } } }, "UnityEnvironment.step": { "total": 335.94022898099684, "count": 18191, "is_parallel": true, "self": 6.255724393925448, "children": { "UnityEnvironment._generate_step_input": { "total": 4.297531260013784, "count": 18191, "is_parallel": true, "self": 4.297531260013784 }, "communicator.exchange": { "total": 306.05458751608967, "count": 18191, "is_parallel": true, "self": 306.05458751608967 }, "steps_from_proto": { "total": 19.332385810967935, "count": 18191, "is_parallel": true, "self": 4.304424856111837, "children": { "_process_rank_one_or_two_observation": { "total": 15.027960954856098, "count": 181910, "is_parallel": true, "self": 15.027960954856098 } } } } } } } } } } }, "trainer_advance": { "total": 106.75934887997755, "count": 18192, "self": 0.5836117989965715, "children": { "process_trajectory": { "total": 23.04976286197507, "count": 18192, "self": 22.1228814709757, "children": { "RLTrainer._checkpoint": { "total": 0.9268813909993696, "count": 4, "self": 0.9268813909993696 } } }, "_update_policy": { "total": 83.12597421900591, "count": 90, "self": 33.79015410698503, "children": { "TorchPPOOptimizer.update": { "total": 49.33582011202088, "count": 4587, "self": 49.33582011202088 } } } } } } }, "trainer_threads": { "total": 9.549994501867332e-07, "count": 1, "self": 9.549994501867332e-07 }, "TrainerController._save_models": { "total": 0.25780902299993613, "count": 1, "self": 0.04604685899994365, "children": { "RLTrainer._checkpoint": { "total": 0.21176216399999248, "count": 1, "self": 0.21176216399999248 } } } } } } }