{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9891510605812073, "min": 0.9891510605812073, "max": 2.8557701110839844, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9444.4140625, "min": 9444.4140625, "max": 29245.94140625, "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": 12.92729377746582, "min": 0.4566662907600403, "max": 12.92729377746582, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.822265625, "min": 88.59326171875, "max": 2598.29541015625, "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": 0.0684112667235704, "min": 0.0626177810715008, "max": 0.07409168027829853, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2736450668942816, "min": 0.2504711242860032, "max": 0.36338475797731684, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20252509700024832, "min": 0.12185078685733435, "max": 0.2981228034285938, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8101003880009933, "min": 0.4874031474293374, "max": 1.4906140171429691, "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": 25.181818181818183, "min": 3.272727272727273, "max": 25.69090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 144.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.272727272727273, "max": 25.69090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 144.0, "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": "1703502597", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703503043" }, "total": 445.105996238, "count": 1, "self": 0.45267629899990425, "children": { "run_training.setup": { "total": 0.06018560500001513, "count": 1, "self": 0.06018560500001513 }, "TrainerController.start_learning": { "total": 444.59313433400007, "count": 1, "self": 0.5747446669897727, "children": { "TrainerController._reset_env": { "total": 3.1772445139999945, "count": 1, "self": 3.1772445139999945 }, "TrainerController.advance": { "total": 440.75570363601037, "count": 18199, "self": 0.27520501498725025, "children": { "env_step": { "total": 440.4804986210231, "count": 18199, "self": 292.153078419007, "children": { "SubprocessEnvManager._take_step": { "total": 148.0476356020215, "count": 18199, "self": 1.4765989680172424, "children": { "TorchPolicy.evaluate": { "total": 146.57103663400426, "count": 18199, "self": 146.57103663400426 } } }, "workers": { "total": 0.27978459999462757, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 443.4296213060104, "count": 18199, "is_parallel": true, "self": 217.05264396302118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005719281999972736, "count": 1, "is_parallel": true, "self": 0.004302326000242829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014169559997299075, "count": 10, "is_parallel": true, "self": 0.0014169559997299075 } } }, "UnityEnvironment.step": { "total": 0.03725192599995353, "count": 1, "is_parallel": true, "self": 0.0007392739998977049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004410869998991984, "count": 1, "is_parallel": true, "self": 0.0004410869998991984 }, "communicator.exchange": { "total": 0.0340443510001478, "count": 1, "is_parallel": true, "self": 0.0340443510001478 }, "steps_from_proto": { "total": 0.0020272140000088257, "count": 1, "is_parallel": true, "self": 0.0004054069997891929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016218070002196328, "count": 10, "is_parallel": true, "self": 0.0016218070002196328 } } } } } } }, "UnityEnvironment.step": { "total": 226.37697734298922, "count": 18198, "is_parallel": true, "self": 10.737356255033546, "children": { "UnityEnvironment._generate_step_input": { "total": 5.236837543976435, "count": 18198, "is_parallel": true, "self": 5.236837543976435 }, "communicator.exchange": { "total": 176.77423544300473, "count": 18198, "is_parallel": true, "self": 176.77423544300473 }, "steps_from_proto": { "total": 33.62854810097451, "count": 18198, "is_parallel": true, "self": 6.2954939729847865, "children": { "_process_rank_one_or_two_observation": { "total": 27.333054127989726, "count": 181980, "is_parallel": true, "self": 27.333054127989726 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017849899995781016, "count": 1, "self": 0.00017849899995781016, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 435.3592134269463, "count": 661695, "is_parallel": true, "self": 13.645342365884517, "children": { "process_trajectory": { "total": 238.73322244306178, "count": 661695, "is_parallel": true, "self": 237.9327127340614, "children": { "RLTrainer._checkpoint": { "total": 0.8005097090003801, "count": 4, "is_parallel": true, "self": 0.8005097090003801 } } }, "_update_policy": { "total": 182.98064861800003, "count": 90, "is_parallel": true, "self": 57.483944799994106, "children": { "TorchPPOOptimizer.update": { "total": 125.49670381800593, "count": 4581, "is_parallel": true, "self": 125.49670381800593 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08526301799997782, "count": 1, "self": 0.0009621209999295388, "children": { "RLTrainer._checkpoint": { "total": 0.08430089700004828, "count": 1, "self": 0.08430089700004828 } } } } } } }