{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9563248753547668, "min": 0.9563248753547668, "max": 2.866558313369751, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9141.509765625, "min": 9141.509765625, "max": 29387.95703125, "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": 12.4596529006958, "min": 0.447489470243454, "max": 12.4596529006958, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2429.63232421875, "min": 86.81295776367188, "max": 2515.973876953125, "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": 0.06685209334268709, "min": 0.0594923568837925, "max": 0.07554675473782517, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26740837337074835, "min": 0.23796942753517, "max": 0.35749361506924626, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.212255578853336, "min": 0.12622052196221537, "max": 0.2793008262620253, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.849022315413344, "min": 0.5048820878488615, "max": 1.3965041313101265, "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": 24.227272727272727, "min": 3.590909090909091, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1066.0, "min": 158.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.227272727272727, "min": 3.590909090909091, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1066.0, "min": 158.0, "max": 1378.0, "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": "1709905853", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709906270" }, "total": 417.26128737400006, "count": 1, "self": 0.4357384690000572, "children": { "run_training.setup": { "total": 0.0539525099999878, "count": 1, "self": 0.0539525099999878 }, "TrainerController.start_learning": { "total": 416.771596395, "count": 1, "self": 0.5197643870038746, "children": { "TrainerController._reset_env": { "total": 2.928468255000041, "count": 1, "self": 2.928468255000041 }, "TrainerController.advance": { "total": 413.2333870589961, "count": 18201, "self": 0.2465838009979393, "children": { "env_step": { "total": 412.98680325799813, "count": 18201, "self": 263.3984585379863, "children": { "SubprocessEnvManager._take_step": { "total": 149.33457030699782, "count": 18201, "self": 1.3513899629946877, "children": { "TorchPolicy.evaluate": { "total": 147.98318034400313, "count": 18201, "self": 147.98318034400313 } } }, "workers": { "total": 0.25377441301401404, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 415.7439114590017, "count": 18201, "is_parallel": true, "self": 209.95735172100126, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005689113000016732, "count": 1, "is_parallel": true, "self": 0.004117699999994784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015714130000219484, "count": 10, "is_parallel": true, "self": 0.0015714130000219484 } } }, "UnityEnvironment.step": { "total": 0.062211289000003944, "count": 1, "is_parallel": true, "self": 0.0006269269999847893, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004109439999524511, "count": 1, "is_parallel": true, "self": 0.0004109439999524511 }, "communicator.exchange": { "total": 0.05920015500004183, "count": 1, "is_parallel": true, "self": 0.05920015500004183 }, "steps_from_proto": { "total": 0.001973263000024872, "count": 1, "is_parallel": true, "self": 0.00037767300000268733, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015955900000221845, "count": 10, "is_parallel": true, "self": 0.0015955900000221845 } } } } } } }, "UnityEnvironment.step": { "total": 205.78655973800045, "count": 18200, "is_parallel": true, "self": 9.717674739994436, "children": { "UnityEnvironment._generate_step_input": { "total": 5.025531775997365, "count": 18200, "is_parallel": true, "self": 5.025531775997365 }, "communicator.exchange": { "total": 159.55853333500642, "count": 18200, "is_parallel": true, "self": 159.55853333500642 }, "steps_from_proto": { "total": 31.48481988700223, "count": 18200, "is_parallel": true, "self": 5.749924848995931, "children": { "_process_rank_one_or_two_observation": { "total": 25.7348950380063, "count": 182000, "is_parallel": true, "self": 25.7348950380063 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013043900003140152, "count": 1, "self": 0.00013043900003140152, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 408.0790063529527, "count": 654823, "is_parallel": true, "self": 13.792041785907998, "children": { "process_trajectory": { "total": 227.51446682604472, "count": 654823, "is_parallel": true, "self": 227.04906721604488, "children": { "RLTrainer._checkpoint": { "total": 0.4653996099998494, "count": 4, "is_parallel": true, "self": 0.4653996099998494 } } }, "_update_policy": { "total": 166.772497741, "count": 90, "is_parallel": true, "self": 47.002004741002565, "children": { "TorchPPOOptimizer.update": { "total": 119.77049299999743, "count": 4584, "is_parallel": true, "self": 119.77049299999743 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08984625499999765, "count": 1, "self": 0.0012080569999852742, "children": { "RLTrainer._checkpoint": { "total": 0.08863819800001238, "count": 1, "self": 0.08863819800001238 } } } } } } }