{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.9315381050109863, "min": 1.9315381050109863, "max": 2.8702282905578613, "count": 7 }, "SnowballTarget.Policy.Entropy.sum": { "value": 19504.671875, "min": 19504.671875, "max": 29551.87109375, "count": 7 }, "SnowballTarget.Step.mean": { "value": 69992.0, "min": 9952.0, "max": 69992.0, "count": 7 }, "SnowballTarget.Step.sum": { "value": 69992.0, "min": 9952.0, "max": 69992.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.592403888702393, "min": 0.3914852440357208, "max": 6.592403888702393, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1285.518798828125, "min": 75.94813537597656, "max": 1285.518798828125, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06854227489398623, "min": 0.06675874077543495, "max": 0.07348860295247042, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27416909957594493, "min": 0.2670349631017398, "max": 0.35985593154684603, "count": 7 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.28034259451954974, "min": 0.1218956601805985, "max": 0.28531403934546545, "count": 7 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.121370378078199, "min": 0.487582640722394, "max": 1.3624117485448426, "count": 7 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00020278203240600001, "min": 0.00020278203240600001, "max": 0.000291882002706, "count": 7 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0008111281296240001, "min": 0.0008111281296240001, "max": 0.00138516003828, "count": 7 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.16759400000000002, "min": 0.16759400000000002, "max": 0.19729400000000002, "count": 7 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6703760000000001, "min": 0.6703760000000001, "max": 0.96172, "count": 7 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.003382940600000001, "min": 0.003382940600000001, "max": 0.0048649706, "count": 7 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.013531762400000005, "min": 0.013531762400000005, "max": 0.023089828, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 15.931818181818182, "min": 3.1136363636363638, "max": 15.931818181818182, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 701.0, "min": 137.0, "max": 774.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 15.931818181818182, "min": 3.1136363636363638, "max": 15.931818181818182, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 701.0, "min": 137.0, "max": 774.0, "count": 7 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719350783", "python_version": "3.10.12 (main, Jun 25 2024, 18:12:47) [GCC 14.1.1 20240522]", "command_line_arguments": "/home/matt/docs/howTo/ai/u5/hf-env/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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719350846" }, "total": 62.97646521600018, "count": 1, "self": 0.1737509720005619, "children": { "run_training.setup": { "total": 0.012011805999463832, "count": 1, "self": 0.012011805999463832 }, "TrainerController.start_learning": { "total": 62.79070243800015, "count": 1, "self": 0.09770760198171047, "children": { "TrainerController._reset_env": { "total": 0.8941725790000419, "count": 1, "self": 0.8941725790000419 }, "TrainerController.advance": { "total": 61.75479988301777, "count": 6556, "self": 0.04473474206406536, "children": { "env_step": { "total": 61.7100651409537, "count": 6556, "self": 44.44529195897121, "children": { "SubprocessEnvManager._take_step": { "total": 17.216592010026034, "count": 6556, "self": 0.2523318360263147, "children": { "TorchPolicy.evaluate": { "total": 16.96426017399972, "count": 6556, "self": 16.96426017399972 } } }, "workers": { "total": 0.04818117195645755, "count": 6555, "self": 0.0, "children": { "worker_root": { "total": 62.655246266022914, "count": 6555, "is_parallel": true, "self": 33.381031464014086, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009580320001987275, "count": 1, "is_parallel": true, "self": 0.00031027200111566344, "children": { "_process_rank_one_or_two_observation": { "total": 0.000647759999083064, "count": 10, "is_parallel": true, "self": 0.000647759999083064 } } }, "UnityEnvironment.step": { "total": 0.014263753000705037, "count": 1, "is_parallel": true, "self": 0.00024890900022001006, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029059400003461633, "count": 1, "is_parallel": true, "self": 0.00029059400003461633 }, "communicator.exchange": { "total": 0.01266807800038805, "count": 1, "is_parallel": true, "self": 0.01266807800038805 }, "steps_from_proto": { "total": 0.001056172000062361, "count": 1, "is_parallel": true, "self": 0.0002604080000310205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007957640000313404, "count": 10, "is_parallel": true, "self": 0.0007957640000313404 } } } } } } }, "UnityEnvironment.step": { "total": 29.274214802008828, "count": 6554, "is_parallel": true, "self": 1.1769603450593422, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6377088219951474, "count": 6554, "is_parallel": true, "self": 0.6377088219951474 }, "communicator.exchange": { "total": 23.746717012966656, "count": 6554, "is_parallel": true, "self": 23.746717012966656 }, "steps_from_proto": { "total": 3.7128286219876827, "count": 6554, "is_parallel": true, "self": 0.7385545441675276, "children": { "_process_rank_one_or_two_observation": { "total": 2.974274077820155, "count": 65540, "is_parallel": true, "self": 2.974274077820155 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.6499000341573264e-05, "count": 1, "self": 2.6499000341573264e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 61.67237820009723, "count": 37409, "is_parallel": true, "self": 0.4198227440856499, "children": { "process_trajectory": { "total": 35.119402948012976, "count": 37409, "is_parallel": true, "self": 35.01569295801255, "children": { "RLTrainer._checkpoint": { "total": 0.10370999000042502, "count": 1, "is_parallel": true, "self": 0.10370999000042502 } } }, "_update_policy": { "total": 26.133152507998602, "count": 32, "is_parallel": true, "self": 7.7936852750335675, "children": { "TorchPPOOptimizer.update": { "total": 18.339467232965035, "count": 1629, "is_parallel": true, "self": 18.339467232965035 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04399587500029156, "count": 1, "self": 0.00040369700036535505, "children": { "RLTrainer._checkpoint": { "total": 0.04359217799992621, "count": 1, "self": 0.04359217799992621 } } } } } } }