{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0661354064941406, "min": 1.0661354064941406, "max": 2.8741071224212646, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10167.7333984375, "min": 10167.7333984375, "max": 29686.65234375, "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": 12.516974449157715, "min": 0.3274807631969452, "max": 12.516974449157715, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2440.81005859375, "min": 63.53126907348633, "max": 2547.41796875, "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": 0.06808326494712104, "min": 0.06264635857101072, "max": 0.0762871209369098, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27233305978848416, "min": 0.26603421973164126, "max": 0.381435604684549, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22062882934423053, "min": 0.10868607821312788, "max": 0.2880108393728733, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8825153173769221, "min": 0.4347443128525115, "max": 1.3491910847963071, "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": 24.772727272727273, "min": 3.159090909090909, "max": 24.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 139.0, "max": 1349.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 3.159090909090909, "max": 24.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 139.0, "max": 1349.0, "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": "1699187434", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699187894" }, "total": 460.187035867, "count": 1, "self": 0.4393367030000377, "children": { "run_training.setup": { "total": 0.04280106099997738, "count": 1, "self": 0.04280106099997738 }, "TrainerController.start_learning": { "total": 459.704898103, "count": 1, "self": 0.5394696250139646, "children": { "TrainerController._reset_env": { "total": 9.484083946999988, "count": 1, "self": 9.484083946999988 }, "TrainerController.advance": { "total": 449.592179868986, "count": 18198, "self": 0.26194966097938277, "children": { "env_step": { "total": 449.33023020800664, "count": 18198, "self": 307.0672063589954, "children": { "SubprocessEnvManager._take_step": { "total": 141.99290833801166, "count": 18198, "self": 1.398014299010356, "children": { "TorchPolicy.evaluate": { "total": 140.5948940390013, "count": 18198, "self": 140.5948940390013 } } }, "workers": { "total": 0.27011551099957387, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 458.4686595420007, "count": 18198, "is_parallel": true, "self": 224.9347675079979, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005556507999983751, "count": 1, "is_parallel": true, "self": 0.004067254000062803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014892539999209475, "count": 10, "is_parallel": true, "self": 0.0014892539999209475 } } }, "UnityEnvironment.step": { "total": 0.035347817999991094, "count": 1, "is_parallel": true, "self": 0.0006528370000182804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003962399999863919, "count": 1, "is_parallel": true, "self": 0.0003962399999863919 }, "communicator.exchange": { "total": 0.032355252999991535, "count": 1, "is_parallel": true, "self": 0.032355252999991535 }, "steps_from_proto": { "total": 0.0019434879999948862, "count": 1, "is_parallel": true, "self": 0.0003661399998691195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015773480001257667, "count": 10, "is_parallel": true, "self": 0.0015773480001257667 } } } } } } }, "UnityEnvironment.step": { "total": 233.5338920340028, "count": 18197, "is_parallel": true, "self": 10.300083994994225, "children": { "UnityEnvironment._generate_step_input": { "total": 5.293530658998179, "count": 18197, "is_parallel": true, "self": 5.293530658998179 }, "communicator.exchange": { "total": 185.39381519200634, "count": 18197, "is_parallel": true, "self": 185.39381519200634 }, "steps_from_proto": { "total": 32.54646218800406, "count": 18197, "is_parallel": true, "self": 5.937295767015883, "children": { "_process_rank_one_or_two_observation": { "total": 26.609166420988174, "count": 181970, "is_parallel": true, "self": 26.609166420988174 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017635200003951468, "count": 1, "self": 0.00017635200003951468, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.886302423949, "count": 468391, "is_parallel": true, "self": 9.767276469959029, "children": { "process_trajectory": { "total": 252.55644104899022, "count": 468391, "is_parallel": true, "self": 251.78493913999034, "children": { "RLTrainer._checkpoint": { "total": 0.7715019089998805, "count": 4, "is_parallel": true, "self": 0.7715019089998805 } } }, "_update_policy": { "total": 183.56258490499977, "count": 90, "is_parallel": true, "self": 54.735048420996065, "children": { "TorchPPOOptimizer.update": { "total": 128.8275364840037, "count": 4587, "is_parallel": true, "self": 128.8275364840037 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08898830999999063, "count": 1, "self": 0.0008963989999983824, "children": { "RLTrainer._checkpoint": { "total": 0.08809191099999225, "count": 1, "self": 0.08809191099999225 } } } } } } }