{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8450688123703003, "min": 0.8450688123703003, "max": 2.8514814376831055, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8031.5341796875, "min": 8031.5341796875, "max": 29107.921875, "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": 12.942442893981934, "min": 0.5654761791229248, "max": 12.942442893981934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.7763671875, "min": 109.70237731933594, "max": 2635.63232421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06887228076926014, "min": 0.06264604988146126, "max": 0.07573135014795744, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27548912307704054, "min": 0.25058419952584504, "max": 0.3786567507397872, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.197972393174674, "min": 0.12043919636155753, "max": 0.3099069744932885, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.791889572698696, "min": 0.48175678544623013, "max": 1.5495348724664426, "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": 25.65909090909091, "min": 3.7954545454545454, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 167.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.7954545454545454, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 167.0, "max": 1404.0, "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": "1738558822", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738559248" }, "total": 426.57178333, "count": 1, "self": 0.44188722199993435, "children": { "run_training.setup": { "total": 0.03260456200001727, "count": 1, "self": 0.03260456200001727 }, "TrainerController.start_learning": { "total": 426.09729154600006, "count": 1, "self": 0.350541433000501, "children": { "TrainerController._reset_env": { "total": 3.407420125000044, "count": 1, "self": 3.407420125000044 }, "TrainerController.advance": { "total": 422.25287429899953, "count": 18192, "self": 0.3486488559964869, "children": { "env_step": { "total": 297.8236921990081, "count": 18192, "self": 226.91088508401054, "children": { "SubprocessEnvManager._take_step": { "total": 70.70133261400508, "count": 18192, "self": 1.242970884995941, "children": { "TorchPolicy.evaluate": { "total": 69.45836172900914, "count": 18192, "self": 69.45836172900914 } } }, "workers": { "total": 0.21147450099249454, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 424.57755988301136, "count": 18192, "is_parallel": true, "self": 225.65075187100433, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007490216999997301, "count": 1, "is_parallel": true, "self": 0.005287294000027032, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022029229999702693, "count": 10, "is_parallel": true, "self": 0.0022029229999702693 } } }, "UnityEnvironment.step": { "total": 0.03487505099997179, "count": 1, "is_parallel": true, "self": 0.0005975559999455982, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039617499999167194, "count": 1, "is_parallel": true, "self": 0.00039617499999167194 }, "communicator.exchange": { "total": 0.03210079900003393, "count": 1, "is_parallel": true, "self": 0.03210079900003393 }, "steps_from_proto": { "total": 0.00178052100000059, "count": 1, "is_parallel": true, "self": 0.0003340500000490465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014464709999515435, "count": 10, "is_parallel": true, "self": 0.0014464709999515435 } } } } } } }, "UnityEnvironment.step": { "total": 198.92680801200703, "count": 18191, "is_parallel": true, "self": 9.542009143001053, "children": { "UnityEnvironment._generate_step_input": { "total": 5.260463762010318, "count": 18191, "is_parallel": true, "self": 5.260463762010318 }, "communicator.exchange": { "total": 153.47416126600245, "count": 18191, "is_parallel": true, "self": 153.47416126600245 }, "steps_from_proto": { "total": 30.650173840993205, "count": 18191, "is_parallel": true, "self": 5.350951831001396, "children": { "_process_rank_one_or_two_observation": { "total": 25.29922200999181, "count": 181910, "is_parallel": true, "self": 25.29922200999181 } } } } } } } } } } }, "trainer_advance": { "total": 124.08053324399492, "count": 18192, "self": 0.4305782599802228, "children": { "process_trajectory": { "total": 27.025836202015057, "count": 18192, "self": 26.462761278015023, "children": { "RLTrainer._checkpoint": { "total": 0.5630749240000341, "count": 4, "self": 0.5630749240000341 } } }, "_update_policy": { "total": 96.62411878199964, "count": 90, "self": 38.96571962100148, "children": { "TorchPPOOptimizer.update": { "total": 57.65839916099816, "count": 4587, "self": 57.65839916099816 } } } } } } }, "trainer_threads": { "total": 8.759999445828726e-07, "count": 1, "self": 8.759999445828726e-07 }, "TrainerController._save_models": { "total": 0.08645481300004576, "count": 1, "self": 0.0008601820001103988, "children": { "RLTrainer._checkpoint": { "total": 0.08559463099993536, "count": 1, "self": 0.08559463099993536 } } } } } } }