{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.890129804611206, "min": 2.890129804611206, "max": 2.890331506729126, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 2034.6513671875, "min": 2034.6513671875, "max": 4323.92919921875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 960.0, "max": 9952.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 960.0, "max": 9952.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1443396359682083, "min": -0.02502424642443657, "max": 0.1443396359682083, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2.1650946140289307, "min": -0.6256061792373657, "max": 2.1650946140289307, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 2.5454545454545454, "min": 2.1818181818181817, "max": 3.090909090909091, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 28.0, "min": 24.0, "max": 34.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 2.5454545454545454, "min": 2.1818181818181817, "max": 3.090909090909091, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 28.0, "min": 24.0, "max": 34.0, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.034890227926000224, "min": 0.034890227926000224, "max": 0.034890227926000224, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.034890227926000224, "min": 0.034890227926000224, "max": 0.034890227926000224, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.09762346715319391, "min": 0.09762346715319391, "max": 0.09762346715319391, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.09762346715319391, "min": 0.09762346715319391, "max": 0.09762346715319391, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.864008712000001e-05, "min": 3.864008712000001e-05, "max": 3.864008712000001e-05, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.864008712000001e-05, "min": 3.864008712000001e-05, "max": 3.864008712000001e-05, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.11287999999999998, "min": 0.11287999999999998, "max": 0.11287999999999998, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.11287999999999998, "min": 0.11287999999999998, "max": 0.11287999999999998, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0006527120000000002, "min": 0.0006527120000000002, "max": 0.0006527120000000002, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006527120000000002, "min": 0.0006527120000000002, "max": 0.0006527120000000002, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701566222", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/venv-ml-agents/bin/mlagents-learn ./config/SnowballTarget.yaml --env=./training-envs-executables/SnowballTarget/SnowballTarget --run-id=SnowballTargetWSL-test1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701566239" }, "total": 17.199973239010433, "count": 1, "self": 0.2171839510265272, "children": { "run_training.setup": { "total": 0.009799769992241636, "count": 1, "self": 0.009799769992241636 }, "TrainerController.start_learning": { "total": 16.972989517991664, "count": 1, "self": 0.00869064818834886, "children": { "TrainerController._reset_env": { "total": 0.7239282900118269, "count": 1, "self": 0.7239282900118269 }, "TrainerController.advance": { "total": 16.16393009980675, "count": 928, "self": 0.008159256947692484, "children": { "env_step": { "total": 12.537758856313303, "count": 928, "self": 6.365368775499519, "children": { "SubprocessEnvManager._take_step": { "total": 6.166461443179287, "count": 928, "self": 0.030128593993140385, "children": { "TorchPolicy.evaluate": { "total": 6.136332849186147, "count": 928, "self": 6.136332849186147 } } }, "workers": { "total": 0.005928637634497136, "count": 928, "self": 0.0, "children": { "worker_root": { "total": 16.826006932911696, "count": 928, "is_parallel": true, "self": 11.035792209702777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001130607008235529, "count": 1, "is_parallel": true, "self": 0.0003167200193274766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008138869889080524, "count": 10, "is_parallel": true, "self": 0.0008138869889080524 } } }, "UnityEnvironment.step": { "total": 0.01490170499891974, "count": 1, "is_parallel": true, "self": 0.000168889993801713, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021973898401483893, "count": 1, "is_parallel": true, "self": 0.00021973898401483893 }, "communicator.exchange": { "total": 0.014041069021914154, "count": 1, "is_parallel": true, "self": 0.014041069021914154 }, "steps_from_proto": { "total": 0.0004720069991890341, "count": 1, "is_parallel": true, "self": 0.0001227590546477586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003492479445412755, "count": 10, "is_parallel": true, "self": 0.0003492479445412755 } } } } } } }, "UnityEnvironment.step": { "total": 5.790214723208919, "count": 927, "is_parallel": true, "self": 0.1281979820341803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.06885534862522036, "count": 927, "is_parallel": true, "self": 0.06885534862522036 }, "communicator.exchange": { "total": 5.234773067117203, "count": 927, "is_parallel": true, "self": 5.234773067117203 }, "steps_from_proto": { "total": 0.35838832543231547, "count": 927, "is_parallel": true, "self": 0.07572059534140863, "children": { "_process_rank_one_or_two_observation": { "total": 0.28266773009090684, "count": 9270, "is_parallel": true, "self": 0.28266773009090684 } } } } } } } } } } }, "trainer_advance": { "total": 3.6180119865457527, "count": 928, "self": 0.01151119646965526, "children": { "process_trajectory": { "total": 1.1729432440770324, "count": 928, "self": 1.1729432440770324 }, "_update_policy": { "total": 2.433557545999065, "count": 1, "self": 0.6060042819590308, "children": { "TorchPPOOptimizer.update": { "total": 1.8275532640400343, "count": 51, "self": 1.8275532640400343 } } } } } } }, "trainer_threads": { "total": 5.53991412743926e-07, "count": 1, "self": 5.53991412743926e-07 }, "TrainerController._save_models": { "total": 0.07643992599332705, "count": 1, "self": 0.00040903297485783696, "children": { "RLTrainer._checkpoint": { "total": 0.07603089301846921, "count": 1, "self": 0.07603089301846921 } } } } } } }