{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.78897225856781, "min": 1.78897225856781, "max": 2.864316940307617, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 18438.9375, "min": 17544.568359375, "max": 29333.470703125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.54301929473877, "min": 0.21325227618217468, "max": 8.54301929473877, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1742.77587890625, "min": 41.370941162109375, "max": 1742.77587890625, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06667943698286727, "min": 0.06035018062610499, "max": 0.07439961132357198, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33339718491433634, "min": 0.24140072250441996, "max": 0.3719980566178599, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.25202795746279694, "min": 0.11628865516361067, "max": 0.28465798853659163, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2601397873139848, "min": 0.4651546206544427, "max": 1.4232899426829582, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.963636363636365, "min": 3.159090909090909, "max": 18.431818181818183, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 988.0, "min": 139.0, "max": 988.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.963636363636365, "min": 3.159090909090909, "max": 18.431818181818183, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 988.0, "min": 139.0, "max": 988.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689681848", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689682116" }, "total": 267.29057009499996, "count": 1, "self": 0.8388692870000227, "children": { "run_training.setup": { "total": 0.0706202779999785, "count": 1, "self": 0.0706202779999785 }, "TrainerController.start_learning": { "total": 266.38108052999996, "count": 1, "self": 0.368218446998128, "children": { "TrainerController._reset_env": { "total": 5.799526347999972, "count": 1, "self": 5.799526347999972 }, "TrainerController.advance": { "total": 259.9661296460019, "count": 9150, "self": 0.1611184470017406, "children": { "env_step": { "total": 259.80501119900015, "count": 9150, "self": 190.70361647200508, "children": { "SubprocessEnvManager._take_step": { "total": 68.9390698189984, "count": 9150, "self": 1.0671401709983002, "children": { "TorchPolicy.evaluate": { "total": 67.8719296480001, "count": 9150, "self": 67.8719296480001 } } }, "workers": { "total": 0.16232490799666266, "count": 9150, "self": 0.0, "children": { "worker_root": { "total": 265.33894798300224, "count": 9150, "is_parallel": true, "self": 123.9304219280038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01150655399999323, "count": 1, "is_parallel": true, "self": 0.008762482000008731, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027440719999844987, "count": 10, "is_parallel": true, "self": 0.0027440719999844987 } } }, "UnityEnvironment.step": { "total": 0.052060235999988436, "count": 1, "is_parallel": true, "self": 0.0004967349998992177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004127540000240515, "count": 1, "is_parallel": true, "self": 0.0004127540000240515 }, "communicator.exchange": { "total": 0.048692961000028845, "count": 1, "is_parallel": true, "self": 0.048692961000028845 }, "steps_from_proto": { "total": 0.0024577860000363216, "count": 1, "is_parallel": true, "self": 0.0004215850000832688, "children": { "_process_rank_one_or_two_observation": { "total": 0.002036200999953053, "count": 10, "is_parallel": true, "self": 0.002036200999953053 } } } } } } }, "UnityEnvironment.step": { "total": 141.40852605499845, "count": 9149, "is_parallel": true, "self": 6.040702013999066, "children": { "UnityEnvironment._generate_step_input": { "total": 3.000974424996116, "count": 9149, "is_parallel": true, "self": 3.000974424996116 }, "communicator.exchange": { "total": 112.07560935200809, "count": 9149, "is_parallel": true, "self": 112.07560935200809 }, "steps_from_proto": { "total": 20.291240263995178, "count": 9149, "is_parallel": true, "self": 3.7189490600056274, "children": { "_process_rank_one_or_two_observation": { "total": 16.57229120398955, "count": 91490, "is_parallel": true, "self": 16.57229120398955 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004887049999524606, "count": 1, "self": 0.0004887049999524606, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 257.9843460510254, "count": 245118, "is_parallel": true, "self": 5.6148538249942135, "children": { "process_trajectory": { "total": 142.47989714003097, "count": 245118, "is_parallel": true, "self": 141.62456826803094, "children": { "RLTrainer._checkpoint": { "total": 0.8553288720000296, "count": 2, "is_parallel": true, "self": 0.8553288720000296 } } }, "_update_policy": { "total": 109.88959508600021, "count": 45, "is_parallel": true, "self": 42.639652686998886, "children": { "TorchPPOOptimizer.update": { "total": 67.24994239900133, "count": 2292, "is_parallel": true, "self": 67.24994239900133 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2467173840000214, "count": 1, "self": 0.0012221989999261496, "children": { "RLTrainer._checkpoint": { "total": 0.24549518500009526, "count": 1, "self": 0.24549518500009526 } } } } } } }