{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.086653232574463, "min": 1.086653232574463, "max": 2.864504814147949, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10447.083984375, "min": 10447.083984375, "max": 29366.904296875, "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": 13.330911636352539, "min": 0.21069779992103577, "max": 13.330911636352539, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2599.52783203125, "min": 40.87537384033203, "max": 2704.16552734375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07416449816596202, "min": 0.0625541375238219, "max": 0.07734726467399514, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29665799266384807, "min": 0.2502165500952876, "max": 0.3679272587001369, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20894125220822352, "min": 0.12348782051327255, "max": 0.3168540243424621, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8357650088328941, "min": 0.4939512820530902, "max": 1.5842701217123107, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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": 26.136363636363637, "min": 3.227272727272727, "max": 26.163636363636364, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1150.0, "min": 142.0, "max": 1439.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.136363636363637, "min": 3.227272727272727, "max": 26.163636363636364, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1150.0, "min": 142.0, "max": 1439.0, "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": "1679148939", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679149398" }, "total": 459.24679347999995, "count": 1, "self": 0.7308913350000239, "children": { "run_training.setup": { "total": 0.1026755759999105, "count": 1, "self": 0.1026755759999105 }, "TrainerController.start_learning": { "total": 458.413226569, "count": 1, "self": 0.5508019450005577, "children": { "TrainerController._reset_env": { "total": 8.415940521000039, "count": 1, "self": 8.415940521000039 }, "TrainerController.advance": { "total": 449.2170894709993, "count": 18210, "self": 0.26425136000693783, "children": { "env_step": { "total": 448.9528381109924, "count": 18210, "self": 325.5211733980027, "children": { "SubprocessEnvManager._take_step": { "total": 123.16942367298293, "count": 18210, "self": 2.160664179992864, "children": { "TorchPolicy.evaluate": { "total": 121.00875949299007, "count": 18210, "self": 121.00875949299007 } } }, "workers": { "total": 0.2622410400067565, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 456.9696637610077, "count": 18210, "is_parallel": true, "self": 218.77623248999998, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005596019999984492, "count": 1, "is_parallel": true, "self": 0.004218552999645908, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013774670003385836, "count": 10, "is_parallel": true, "self": 0.0013774670003385836 } } }, "UnityEnvironment.step": { "total": 0.03492219300005672, "count": 1, "is_parallel": true, "self": 0.0004460760001165909, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003028339999673335, "count": 1, "is_parallel": true, "self": 0.0003028339999673335 }, "communicator.exchange": { "total": 0.032638415999826975, "count": 1, "is_parallel": true, "self": 0.032638415999826975 }, "steps_from_proto": { "total": 0.0015348670001458231, "count": 1, "is_parallel": true, "self": 0.00034344099981353793, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011914260003322852, "count": 10, "is_parallel": true, "self": 0.0011914260003322852 } } } } } } }, "UnityEnvironment.step": { "total": 238.19343127100774, "count": 18209, "is_parallel": true, "self": 9.388630260035598, "children": { "UnityEnvironment._generate_step_input": { "total": 5.070005011990133, "count": 18209, "is_parallel": true, "self": 5.070005011990133 }, "communicator.exchange": { "total": 192.926280372993, "count": 18209, "is_parallel": true, "self": 192.926280372993 }, "steps_from_proto": { "total": 30.808515625989003, "count": 18209, "is_parallel": true, "self": 6.022158589000128, "children": { "_process_rank_one_or_two_observation": { "total": 24.786357036988875, "count": 182090, "is_parallel": true, "self": 24.786357036988875 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011431699999775446, "count": 1, "self": 0.00011431699999775446, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.9823782119595, "count": 393118, "is_parallel": true, "self": 9.326574058871529, "children": { "process_trajectory": { "total": 246.15956744908794, "count": 393118, "is_parallel": true, "self": 245.00893815708787, "children": { "RLTrainer._checkpoint": { "total": 1.150629292000076, "count": 4, "is_parallel": true, "self": 1.150629292000076 } } }, "_update_policy": { "total": 190.496236704, "count": 90, "is_parallel": true, "self": 71.96154976500156, "children": { "TorchPPOOptimizer.update": { "total": 118.53468693899845, "count": 4587, "is_parallel": true, "self": 118.53468693899845 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22928031500009638, "count": 1, "self": 0.001243378000026496, "children": { "RLTrainer._checkpoint": { "total": 0.22803693700006988, "count": 1, "self": 0.22803693700006988 } } } } } } }