{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9911953806877136, "min": 0.9911953806877136, "max": 2.8682048320770264, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9463.93359375, "min": 9463.93359375, "max": 29373.28515625, "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": 11.87179946899414, "min": 0.3513963520526886, "max": 11.87179946899414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2315.0009765625, "min": 68.17089080810547, "max": 2397.58642578125, "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": 0.06692388449305683, "min": 0.05886616089561607, "max": 0.07428211850326669, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26769553797222734, "min": 0.25812034749234203, "max": 0.361638882818678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18812231916715116, "min": 0.12231371497310808, "max": 0.2853779008283335, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7524892766686047, "min": 0.48925485989243234, "max": 1.4181817258689917, "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": 24.0, "min": 3.3863636363636362, "max": 24.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 149.0, "max": 1265.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.3863636363636362, "max": 24.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 149.0, "max": 1265.0, "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": "1701701762", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701702218" }, "total": 456.89337141100003, "count": 1, "self": 0.4382369720000838, "children": { "run_training.setup": { "total": 0.05653066399997897, "count": 1, "self": 0.05653066399997897 }, "TrainerController.start_learning": { "total": 456.39860377499997, "count": 1, "self": 0.5368702609989668, "children": { "TrainerController._reset_env": { "total": 3.5086109650000026, "count": 1, "self": 3.5086109650000026 }, "TrainerController.advance": { "total": 452.264530876001, "count": 18199, "self": 0.23963208900568134, "children": { "env_step": { "total": 452.0248987869953, "count": 18199, "self": 306.5228481419985, "children": { "SubprocessEnvManager._take_step": { "total": 145.2441972079975, "count": 18199, "self": 1.3666047189985306, "children": { "TorchPolicy.evaluate": { "total": 143.87759248899897, "count": 18199, "self": 143.87759248899897 } } }, "workers": { "total": 0.2578534369993122, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 455.17338676499406, "count": 18199, "is_parallel": true, "self": 223.63054580899956, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005990834999977324, "count": 1, "is_parallel": true, "self": 0.004400176999922678, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015906580000546455, "count": 10, "is_parallel": true, "self": 0.0015906580000546455 } } }, "UnityEnvironment.step": { "total": 0.08011985000001687, "count": 1, "is_parallel": true, "self": 0.0007373739999820828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037961700002142607, "count": 1, "is_parallel": true, "self": 0.00037961700002142607 }, "communicator.exchange": { "total": 0.07703956599999628, "count": 1, "is_parallel": true, "self": 0.07703956599999628 }, "steps_from_proto": { "total": 0.0019632930000170745, "count": 1, "is_parallel": true, "self": 0.00033604899994088555, "children": { "_process_rank_one_or_two_observation": { "total": 0.001627244000076189, "count": 10, "is_parallel": true, "self": 0.001627244000076189 } } } } } } }, "UnityEnvironment.step": { "total": 231.5428409559945, "count": 18198, "is_parallel": true, "self": 10.298755066002741, "children": { "UnityEnvironment._generate_step_input": { "total": 5.144804924997061, "count": 18198, "is_parallel": true, "self": 5.144804924997061 }, "communicator.exchange": { "total": 183.7255130689934, "count": 18198, "is_parallel": true, "self": 183.7255130689934 }, "steps_from_proto": { "total": 32.37376789600131, "count": 18198, "is_parallel": true, "self": 5.931723867978235, "children": { "_process_rank_one_or_two_observation": { "total": 26.442044028023076, "count": 181980, "is_parallel": true, "self": 26.442044028023076 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018241899999793532, "count": 1, "self": 0.00018241899999793532, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.53862828099716, "count": 484608, "is_parallel": true, "self": 10.087065409013519, "children": { "process_trajectory": { "total": 254.39220740498394, "count": 484608, "is_parallel": true, "self": 253.59886836798404, "children": { "RLTrainer._checkpoint": { "total": 0.793339036999896, "count": 4, "is_parallel": true, "self": 0.793339036999896 } } }, "_update_policy": { "total": 184.0593554669997, "count": 90, "is_parallel": true, "self": 56.67302943300291, "children": { "TorchPPOOptimizer.update": { "total": 127.3863260339968, "count": 4587, "is_parallel": true, "self": 127.3863260339968 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08840925399999833, "count": 1, "self": 0.0008606020001025172, "children": { "RLTrainer._checkpoint": { "total": 0.08754865199989581, "count": 1, "self": 0.08754865199989581 } } } } } } }