{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8908392190933228, "min": 0.8908392190933228, "max": 2.866718053817749, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8525.3310546875, "min": 8525.3310546875, "max": 29358.05859375, "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": 13.036944389343262, "min": 0.38574761152267456, "max": 13.036944389343262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.2041015625, "min": 74.83503723144531, "max": 2648.642578125, "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": 0.06549415023661875, "min": 0.06259190532136036, "max": 0.07378887098474318, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.261976600946475, "min": 0.25036762128544143, "max": 0.3689443549237159, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1959238492828958, "min": 0.10229353375924644, "max": 0.29001620221956104, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7836953971315832, "min": 0.40917413503698574, "max": 1.3734550876360314, "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": 25.522727272727273, "min": 3.2045454545454546, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 141.0, "max": 1427.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.2045454545454546, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 141.0, "max": 1427.0, "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": "1693561168", "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": "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": "1693561753" }, "total": 584.2757537140001, "count": 1, "self": 0.7951858229999971, "children": { "run_training.setup": { "total": 0.044325329000002966, "count": 1, "self": 0.044325329000002966 }, "TrainerController.start_learning": { "total": 583.4362425620001, "count": 1, "self": 0.7207266580181795, "children": { "TrainerController._reset_env": { "total": 5.2497518899999704, "count": 1, "self": 5.2497518899999704 }, "TrainerController.advance": { "total": 577.1815487169818, "count": 18228, "self": 0.36195562498301115, "children": { "env_step": { "total": 576.8195930919987, "count": 18228, "self": 421.90080682902146, "children": { "SubprocessEnvManager._take_step": { "total": 154.55587550098278, "count": 18228, "self": 2.3943393629848515, "children": { "TorchPolicy.evaluate": { "total": 152.16153613799793, "count": 18228, "self": 152.16153613799793 } } }, "workers": { "total": 0.3629107619944989, "count": 18228, "self": 0.0, "children": { "worker_root": { "total": 581.1901793749948, "count": 18228, "is_parallel": true, "self": 268.1798842320011, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006264316000056169, "count": 1, "is_parallel": true, "self": 0.004548879000253692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017154369998024777, "count": 10, "is_parallel": true, "self": 0.0017154369998024777 } } }, "UnityEnvironment.step": { "total": 0.07945649299995239, "count": 1, "is_parallel": true, "self": 0.0006451420000530561, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044214499996542145, "count": 1, "is_parallel": true, "self": 0.00044214499996542145 }, "communicator.exchange": { "total": 0.07583715499993104, "count": 1, "is_parallel": true, "self": 0.07583715499993104 }, "steps_from_proto": { "total": 0.002532051000002866, "count": 1, "is_parallel": true, "self": 0.0006157840001606019, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019162669998422643, "count": 10, "is_parallel": true, "self": 0.0019162669998422643 } } } } } } }, "UnityEnvironment.step": { "total": 313.01029514299375, "count": 18227, "is_parallel": true, "self": 13.04874133499277, "children": { "UnityEnvironment._generate_step_input": { "total": 6.829024186988363, "count": 18227, "is_parallel": true, "self": 6.829024186988363 }, "communicator.exchange": { "total": 246.50912921399788, "count": 18227, "is_parallel": true, "self": 246.50912921399788 }, "steps_from_proto": { "total": 46.62340040701474, "count": 18227, "is_parallel": true, "self": 8.80832426600739, "children": { "_process_rank_one_or_two_observation": { "total": 37.81507614100735, "count": 182270, "is_parallel": true, "self": 37.81507614100735 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011927600007766159, "count": 1, "self": 0.00011927600007766159, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 572.010526614037, "count": 544916, "is_parallel": true, "self": 13.53440163508651, "children": { "process_trajectory": { "total": 317.99035542195134, "count": 544916, "is_parallel": true, "self": 315.16366147295116, "children": { "RLTrainer._checkpoint": { "total": 2.8266939490001732, "count": 4, "is_parallel": true, "self": 2.8266939490001732 } } }, "_update_policy": { "total": 240.48576955699912, "count": 90, "is_parallel": true, "self": 94.35345612599951, "children": { "TorchPPOOptimizer.update": { "total": 146.1323134309996, "count": 4587, "is_parallel": true, "self": 146.1323134309996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2840960210000958, "count": 1, "self": 0.0012537100001281942, "children": { "RLTrainer._checkpoint": { "total": 0.2828423109999676, "count": 1, "self": 0.2828423109999676 } } } } } } }