{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8433678150177002, "min": 0.8433678150177002, "max": 2.876692295074463, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8089.583984375, "min": 8089.583984375, "max": 29523.4921875, "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": 12.562338829040527, "min": 0.3045682907104492, "max": 12.562338829040527, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2449.656005859375, "min": 59.086246490478516, "max": 2544.81201171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06955747328189033, "min": 0.06347808780036776, "max": 0.0778183127045172, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2782298931275613, "min": 0.26456724547361044, "max": 0.38909156352258595, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18286100179687434, "min": 0.10406067052527385, "max": 0.31107451189674584, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7314440071874974, "min": 0.4162426821010954, "max": 1.3185881887580835, "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": 24.90909090909091, "min": 2.7954545454545454, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 123.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 2.7954545454545454, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 123.0, "max": 1367.0, "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": "1724308769", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/ai24/miniconda3/envs/hfrl5/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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724309031" }, "total": 262.2257207769999, "count": 1, "self": 0.16705240500004948, "children": { "run_training.setup": { "total": 0.008200049999686598, "count": 1, "self": 0.008200049999686598 }, "TrainerController.start_learning": { "total": 262.05046832200014, "count": 1, "self": 0.2289661809872996, "children": { "TrainerController._reset_env": { "total": 0.8576892099999895, "count": 1, "self": 0.8576892099999895 }, "TrainerController.advance": { "total": 260.9249573480124, "count": 18205, "self": 0.09760793400209877, "children": { "env_step": { "total": 260.8273494140103, "count": 18205, "self": 159.8796721990775, "children": { "SubprocessEnvManager._take_step": { "total": 100.8444341919585, "count": 18205, "self": 0.590002356984769, "children": { "TorchPolicy.evaluate": { "total": 100.25443183497373, "count": 18205, "self": 100.25443183497373 } } }, "workers": { "total": 0.10324302297431132, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 261.5922094690068, "count": 18205, "is_parallel": true, "self": 143.6301278050155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001378724999995029, "count": 1, "is_parallel": true, "self": 0.000588105999668187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007906190003268421, "count": 10, "is_parallel": true, "self": 0.0007906190003268421 } } }, "UnityEnvironment.step": { "total": 0.013282175999847823, "count": 1, "is_parallel": true, "self": 0.00014913999939381029, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00011576099996091216, "count": 1, "is_parallel": true, "self": 0.00011576099996091216 }, "communicator.exchange": { "total": 0.012613349000275775, "count": 1, "is_parallel": true, "self": 0.012613349000275775 }, "steps_from_proto": { "total": 0.00040392600021732505, "count": 1, "is_parallel": true, "self": 9.560400030750316e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003083219999098219, "count": 10, "is_parallel": true, "self": 0.0003083219999098219 } } } } } } }, "UnityEnvironment.step": { "total": 117.96208166399128, "count": 18204, "is_parallel": true, "self": 2.4290411579868305, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3298345210114348, "count": 18204, "is_parallel": true, "self": 1.3298345210114348 }, "communicator.exchange": { "total": 107.47794991296541, "count": 18204, "is_parallel": true, "self": 107.47794991296541 }, "steps_from_proto": { "total": 6.725256072027605, "count": 18204, "is_parallel": true, "self": 1.430365531901316, "children": { "_process_rank_one_or_two_observation": { "total": 5.294890540126289, "count": 182040, "is_parallel": true, "self": 5.294890540126289 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.346100033420953e-05, "count": 1, "self": 5.346100033420953e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 260.2897595271702, "count": 223572, "is_parallel": true, "self": 2.0270521112179267, "children": { "process_trajectory": { "total": 143.1991481739533, "count": 223572, "is_parallel": true, "self": 142.80432441595303, "children": { "RLTrainer._checkpoint": { "total": 0.39482375800025693, "count": 4, "is_parallel": true, "self": 0.39482375800025693 } } }, "_update_policy": { "total": 115.06355924199897, "count": 90, "is_parallel": true, "self": 13.432681314997353, "children": { "TorchPPOOptimizer.update": { "total": 101.63087792700162, "count": 4587, "is_parallel": true, "self": 101.63087792700162 } } } } } } } } }, "TrainerController._save_models": { "total": 0.038802122000106465, "count": 1, "self": 0.00031995700010156725, "children": { "RLTrainer._checkpoint": { "total": 0.0384821650000049, "count": 1, "self": 0.0384821650000049 } } } } } } }