{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8834794163703918, "min": 0.8834794163703918, "max": 2.868428945541382, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8445.1796875, "min": 8445.1796875, "max": 29407.1328125, "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": 13.023385047912598, "min": 0.3193320631980896, "max": 13.023385047912598, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.56005859375, "min": 61.95042037963867, "max": 2656.127197265625, "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": 0.07784189065219549, "min": 0.059780211634657174, "max": 0.07784189065219549, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.31136756260878196, "min": 0.2391208465386287, "max": 0.3702182697920316, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20739196197075002, "min": 0.11852425636778421, "max": 0.2715981929909949, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8295678478830001, "min": 0.47409702547113686, "max": 1.3454750028311038, "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": 25.40909090909091, "min": 3.25, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 143.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.25, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 143.0, "max": 1413.0, "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": "1696774166", "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": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696774658" }, "total": 491.871324746, "count": 1, "self": 0.43231066099997406, "children": { "run_training.setup": { "total": 0.04756477199998699, "count": 1, "self": 0.04756477199998699 }, "TrainerController.start_learning": { "total": 491.39144931300007, "count": 1, "self": 0.5811471889908262, "children": { "TrainerController._reset_env": { "total": 7.0698960319998605, "count": 1, "self": 7.0698960319998605 }, "TrainerController.advance": { "total": 483.6546885230093, "count": 18201, "self": 0.2844324010177388, "children": { "env_step": { "total": 483.3702561219916, "count": 18201, "self": 330.0816031379761, "children": { "SubprocessEnvManager._take_step": { "total": 152.98760516699735, "count": 18201, "self": 1.5248774169986063, "children": { "TorchPolicy.evaluate": { "total": 151.46272774999875, "count": 18201, "self": 151.46272774999875 } } }, "workers": { "total": 0.3010478170181159, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 490.04162472400617, "count": 18201, "is_parallel": true, "self": 242.10990490603376, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020512599999165104, "count": 1, "is_parallel": true, "self": 0.0006240779996460333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014271820002704771, "count": 10, "is_parallel": true, "self": 0.0014271820002704771 } } }, "UnityEnvironment.step": { "total": 0.04675313100005951, "count": 1, "is_parallel": true, "self": 0.0005086959999971441, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003155619999688497, "count": 1, "is_parallel": true, "self": 0.0003155619999688497 }, "communicator.exchange": { "total": 0.04373305800004346, "count": 1, "is_parallel": true, "self": 0.04373305800004346 }, "steps_from_proto": { "total": 0.002195815000050061, "count": 1, "is_parallel": true, "self": 0.00041017900002771057, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017856360000223503, "count": 10, "is_parallel": true, "self": 0.0017856360000223503 } } } } } } }, "UnityEnvironment.step": { "total": 247.9317198179724, "count": 18200, "is_parallel": true, "self": 10.752826836962868, "children": { "UnityEnvironment._generate_step_input": { "total": 5.726102307001838, "count": 18200, "is_parallel": true, "self": 5.726102307001838 }, "communicator.exchange": { "total": 192.21879729201532, "count": 18200, "is_parallel": true, "self": 192.21879729201532 }, "steps_from_proto": { "total": 39.23399338199238, "count": 18200, "is_parallel": true, "self": 7.295218078981634, "children": { "_process_rank_one_or_two_observation": { "total": 31.938775303010743, "count": 182000, "is_parallel": true, "self": 31.938775303010743 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012005799999315059, "count": 1, "self": 0.00012005799999315059, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.7306149739659, "count": 481493, "is_parallel": true, "self": 10.542159498961837, "children": { "process_trajectory": { "total": 265.88881428400305, "count": 481493, "is_parallel": true, "self": 265.0765392440028, "children": { "RLTrainer._checkpoint": { "total": 0.8122750400002587, "count": 4, "is_parallel": true, "self": 0.8122750400002587 } } }, "_update_policy": { "total": 203.299641191001, "count": 90, "is_parallel": true, "self": 73.78868881300059, "children": { "TorchPPOOptimizer.update": { "total": 129.5109523780004, "count": 4587, "is_parallel": true, "self": 129.5109523780004 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08559751100005997, "count": 1, "self": 0.0008946180000748427, "children": { "RLTrainer._checkpoint": { "total": 0.08470289299998512, "count": 1, "self": 0.08470289299998512 } } } } } } }