{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.921180009841919, "min": 0.9150704145431519, "max": 2.865511894226074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8795.4267578125, "min": 8795.4267578125, "max": 29345.70703125, "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": 12.957006454467773, "min": 0.4872038960456848, "max": 12.957006454467773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.6162109375, "min": 94.5175552368164, "max": 2620.416259765625, "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": 0.06660175781315261, "min": 0.061964006947956105, "max": 0.08024299506947125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26640703125261045, "min": 0.26519743065057577, "max": 0.39332837837533663, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20816557715628659, "min": 0.13706630217390792, "max": 0.3122445605549158, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8326623086251463, "min": 0.5482652086956317, "max": 1.561222802774579, "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": 25.818181818181817, "min": 3.977272727272727, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 175.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.977272727272727, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 175.0, "max": 1406.0, "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": "1673382333", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1.21.6", "end_time_seconds": "1673382748" }, "total": 414.871778221, "count": 1, "self": 0.3914583500001072, "children": { "run_training.setup": { "total": 0.10704335200000514, "count": 1, "self": 0.10704335200000514 }, "TrainerController.start_learning": { "total": 414.3732765189999, "count": 1, "self": 0.46587770301357523, "children": { "TrainerController._reset_env": { "total": 6.907889522000005, "count": 1, "self": 6.907889522000005 }, "TrainerController.advance": { "total": 406.8805550219862, "count": 18202, "self": 0.2410365029853665, "children": { "env_step": { "total": 406.63951851900083, "count": 18202, "self": 265.12046312502355, "children": { "SubprocessEnvManager._take_step": { "total": 141.2679139319855, "count": 18202, "self": 1.3260131429764215, "children": { "TorchPolicy.evaluate": { "total": 139.94190078900908, "count": 18202, "self": 31.611074560013776, "children": { "TorchPolicy.sample_actions": { "total": 108.3308262289953, "count": 18202, "self": 108.3308262289953 } } } } }, "workers": { "total": 0.25114146199177867, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 413.2313255750014, "count": 18202, "is_parallel": true, "self": 199.31190824100906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005492267000022366, "count": 1, "is_parallel": true, "self": 0.0028875710000875188, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026046959999348474, "count": 10, "is_parallel": true, "self": 0.0026046959999348474 } } }, "UnityEnvironment.step": { "total": 0.03232557400008318, "count": 1, "is_parallel": true, "self": 0.0005219209999722807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033202600002368854, "count": 1, "is_parallel": true, "self": 0.00033202600002368854 }, "communicator.exchange": { "total": 0.02965093100010563, "count": 1, "is_parallel": true, "self": 0.02965093100010563 }, "steps_from_proto": { "total": 0.0018206959999815808, "count": 1, "is_parallel": true, "self": 0.0004298529999005041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013908430000810768, "count": 10, "is_parallel": true, "self": 0.0013908430000810768 } } } } } } }, "UnityEnvironment.step": { "total": 213.91941733399233, "count": 18201, "is_parallel": true, "self": 8.273946244020522, "children": { "UnityEnvironment._generate_step_input": { "total": 4.9100422929855085, "count": 18201, "is_parallel": true, "self": 4.9100422929855085 }, "communicator.exchange": { "total": 171.02435885699435, "count": 18201, "is_parallel": true, "self": 171.02435885699435 }, "steps_from_proto": { "total": 29.711069939991944, "count": 18201, "is_parallel": true, "self": 6.214064044017505, "children": { "_process_rank_one_or_two_observation": { "total": 23.49700589597444, "count": 182010, "is_parallel": true, "self": 23.49700589597444 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.9455999967685784e-05, "count": 1, "self": 3.9455999967685784e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 404.14941715504654, "count": 331464, "is_parallel": true, "self": 8.303332546055003, "children": { "process_trajectory": { "total": 231.40938549999112, "count": 331464, "is_parallel": true, "self": 230.5763358599911, "children": { "RLTrainer._checkpoint": { "total": 0.8330496400000129, "count": 4, "is_parallel": true, "self": 0.8330496400000129 } } }, "_update_policy": { "total": 164.43669910900041, "count": 90, "is_parallel": true, "self": 43.15459558699877, "children": { "TorchPPOOptimizer.update": { "total": 121.28210352200165, "count": 4587, "is_parallel": true, "self": 121.28210352200165 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11891481600014231, "count": 1, "self": 0.0008332220002102986, "children": { "RLTrainer._checkpoint": { "total": 0.11808159399993201, "count": 1, "self": 0.11808159399993201 } } } } } } }