{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9005475044250488, "min": 0.9005475044250488, "max": 2.8607847690582275, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8628.1455078125, "min": 8628.1455078125, "max": 29360.234375, "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": 12.367480278015137, "min": 0.47867733240127563, "max": 12.367480278015137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2411.65869140625, "min": 92.8634033203125, "max": 2492.95849609375, "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": 0.07193309414910622, "min": 0.06496866783926117, "max": 0.07334948145680577, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28773237659642487, "min": 0.26225562125225277, "max": 0.35403260225247524, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19404699609560125, "min": 0.13787868416037263, "max": 0.2674171412107991, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.776187984382405, "min": 0.5515147366414905, "max": 1.3370857060539956, "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": 24.59090909090909, "min": 3.8863636363636362, "max": 24.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1082.0, "min": 171.0, "max": 1343.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.59090909090909, "min": 3.8863636363636362, "max": 24.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1082.0, "min": 171.0, "max": 1343.0, "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": "1705559575", "python_version": "3.10.12 (main, Jan 18 2024, 15:14:31) [GCC 11.4.0]", "command_line_arguments": "/home/omar/.pyenv/versions/3.10.12/envs/rlhf/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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705559715" }, "total": 139.82007515500027, "count": 1, "self": 0.16807208099999116, "children": { "run_training.setup": { "total": 0.01136207900071895, "count": 1, "self": 0.01136207900071895 }, "TrainerController.start_learning": { "total": 139.64064099499956, "count": 1, "self": 0.17696914500811545, "children": { "TrainerController._reset_env": { "total": 0.5956832889996804, "count": 1, "self": 0.5956832889996804 }, "TrainerController.advance": { "total": 138.835049959991, "count": 18203, "self": 0.08580434197210707, "children": { "env_step": { "total": 138.7492456180189, "count": 18203, "self": 91.25334967593335, "children": { "SubprocessEnvManager._take_step": { "total": 47.40409384700433, "count": 18203, "self": 0.4959809040683467, "children": { "TorchPolicy.evaluate": { "total": 46.908112942935986, "count": 18203, "self": 46.908112942935986 } } }, "workers": { "total": 0.09180209508122061, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 139.4290607889261, "count": 18203, "is_parallel": true, "self": 75.23505368691167, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009017000002131681, "count": 1, "is_parallel": true, "self": 0.00023257699831447098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006691230018986971, "count": 10, "is_parallel": true, "self": 0.0006691230018986971 } } }, "UnityEnvironment.step": { "total": 0.01114338199931808, "count": 1, "is_parallel": true, "self": 0.00013881899849366164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014191900027071824, "count": 1, "is_parallel": true, "self": 0.00014191900027071824 }, "communicator.exchange": { "total": 0.010380309000538546, "count": 1, "is_parallel": true, "self": 0.010380309000538546 }, "steps_from_proto": { "total": 0.00048233500001515495, "count": 1, "is_parallel": true, "self": 0.00011287899906164967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003694560009535053, "count": 10, "is_parallel": true, "self": 0.0003694560009535053 } } } } } } }, "UnityEnvironment.step": { "total": 64.19400710201444, "count": 18202, "is_parallel": true, "self": 2.2622487519784045, "children": { "UnityEnvironment._generate_step_input": { "total": 1.5764409060357139, "count": 18202, "is_parallel": true, "self": 1.5764409060357139 }, "communicator.exchange": { "total": 52.79206003200761, "count": 18202, "is_parallel": true, "self": 52.79206003200761 }, "steps_from_proto": { "total": 7.5632574119927085, "count": 18202, "is_parallel": true, "self": 1.3852874528993198, "children": { "_process_rank_one_or_two_observation": { "total": 6.177969959093389, "count": 182020, "is_parallel": true, "self": 6.177969959093389 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.6410000575415324e-05, "count": 1, "self": 3.6410000575415324e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 138.757011344077, "count": 89532, "is_parallel": true, "self": 0.6065647880204779, "children": { "process_trajectory": { "total": 73.65652750705067, "count": 89532, "is_parallel": true, "self": 73.44130639705054, "children": { "RLTrainer._checkpoint": { "total": 0.21522111000012956, "count": 4, "is_parallel": true, "self": 0.21522111000012956 } } }, "_update_policy": { "total": 64.49391904900585, "count": 90, "is_parallel": true, "self": 20.85354085498784, "children": { "TorchPPOOptimizer.update": { "total": 43.64037819401801, "count": 4587, "is_parallel": true, "self": 43.64037819401801 } } } } } } } } }, "TrainerController._save_models": { "total": 0.03290219100017566, "count": 1, "self": 0.0004682849994424032, "children": { "RLTrainer._checkpoint": { "total": 0.03243390600073326, "count": 1, "self": 0.03243390600073326 } } } } } } }