{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1315261125564575, "min": 1.1315261125564575, "max": 2.866731882095337, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10803.8115234375, "min": 10803.8115234375, "max": 29358.201171875, "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": 11.664238929748535, "min": 0.32836055755615234, "max": 11.664238929748535, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2274.526611328125, "min": 63.70195007324219, "max": 2347.70068359375, "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": 0.06580828599758473, "min": 0.059406705498558414, "max": 0.07419471178390999, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632331439903389, "min": 0.23762682199423366, "max": 0.3709735589195499, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20391402751499532, "min": 0.12269147837251498, "max": 0.27959091312745044, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8156561100599813, "min": 0.49076591349005994, "max": 1.397954565637252, "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": 23.068181818181817, "min": 3.659090909090909, "max": 23.30909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1015.0, "min": 161.0, "max": 1282.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.068181818181817, "min": 3.659090909090909, "max": 23.30909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1015.0, "min": 161.0, "max": 1282.0, "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": "1677984295", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677984743" }, "total": 447.1178790409999, "count": 1, "self": 0.4395456009999634, "children": { "run_training.setup": { "total": 0.11283896800000548, "count": 1, "self": 0.11283896800000548 }, "TrainerController.start_learning": { "total": 446.56549447199995, "count": 1, "self": 0.5046759709919115, "children": { "TrainerController._reset_env": { "total": 8.469980519000046, "count": 1, "self": 8.469980519000046 }, "TrainerController.advance": { "total": 437.47616184200774, "count": 18202, "self": 0.2679862919910647, "children": { "env_step": { "total": 437.2081755500167, "count": 18202, "self": 300.54456409402746, "children": { "SubprocessEnvManager._take_step": { "total": 136.40464320099568, "count": 18202, "self": 1.5854118519830536, "children": { "TorchPolicy.evaluate": { "total": 134.81923134901263, "count": 18202, "self": 29.924553437013856, "children": { "TorchPolicy.sample_actions": { "total": 104.89467791199877, "count": 18202, "self": 104.89467791199877 } } } } }, "workers": { "total": 0.25896825499353326, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 444.98550698899385, "count": 18202, "is_parallel": true, "self": 215.0479711279918, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00566697500016744, "count": 1, "is_parallel": true, "self": 0.0038133969999307737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018535780002366664, "count": 10, "is_parallel": true, "self": 0.0018535780002366664 } } }, "UnityEnvironment.step": { "total": 0.04412262499999997, "count": 1, "is_parallel": true, "self": 0.000605552999786596, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037383800008683465, "count": 1, "is_parallel": true, "self": 0.00037383800008683465 }, "communicator.exchange": { "total": 0.03812111100000948, "count": 1, "is_parallel": true, "self": 0.03812111100000948 }, "steps_from_proto": { "total": 0.0050221230001170625, "count": 1, "is_parallel": true, "self": 0.0015234700001656165, "children": { "_process_rank_one_or_two_observation": { "total": 0.003498652999951446, "count": 10, "is_parallel": true, "self": 0.003498652999951446 } } } } } } }, "UnityEnvironment.step": { "total": 229.93753586100206, "count": 18201, "is_parallel": true, "self": 9.297244466984012, "children": { "UnityEnvironment._generate_step_input": { "total": 5.110662752016651, "count": 18201, "is_parallel": true, "self": 5.110662752016651 }, "communicator.exchange": { "total": 185.9511595570034, "count": 18201, "is_parallel": true, "self": 185.9511595570034 }, "steps_from_proto": { "total": 29.578469084998005, "count": 18201, "is_parallel": true, "self": 6.383761501926983, "children": { "_process_rank_one_or_two_observation": { "total": 23.194707583071022, "count": 182010, "is_parallel": true, "self": 23.194707583071022 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010859000008167641, "count": 1, "self": 0.00010859000008167641, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 434.33990618509756, "count": 394021, "is_parallel": true, "self": 9.37665533512859, "children": { "process_trajectory": { "total": 249.58640407596909, "count": 394021, "is_parallel": true, "self": 248.83742471796904, "children": { "RLTrainer._checkpoint": { "total": 0.7489793580000423, "count": 4, "is_parallel": true, "self": 0.7489793580000423 } } }, "_update_policy": { "total": 175.3768467739999, "count": 90, "is_parallel": true, "self": 60.581328682015055, "children": { "TorchPPOOptimizer.update": { "total": 114.79551809198483, "count": 4587, "is_parallel": true, "self": 114.79551809198483 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11456755000017438, "count": 1, "self": 0.0008323670001573191, "children": { "RLTrainer._checkpoint": { "total": 0.11373518300001706, "count": 1, "self": 0.11373518300001706 } } } } } } }