{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9602733850479126, "min": 0.9602733850479126, "max": 2.8767659664154053, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9189.81640625, "min": 9189.81640625, "max": 29524.248046875, "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": 12.730972290039062, "min": 0.4604688882827759, "max": 12.730972290039062, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2482.53955078125, "min": 89.33096313476562, "max": 2583.59716796875, "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": 0.073274673446933, "min": 0.05915192100613186, "max": 0.07825943691369841, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.293098693787732, "min": 0.23660768402452745, "max": 0.39129718456849205, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18814506053048022, "min": 0.1088935895514784, "max": 0.28882513691981637, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7525802421219209, "min": 0.4355743582059136, "max": 1.3912319488385145, "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": 25.227272727272727, "min": 3.0681818181818183, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 135.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.0681818181818183, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 135.0, "max": 1380.0, "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": "1720849542", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/home/shinnigus/.local/bin/mlagents-learn /home/shinnigus/huggingface-deeprl/notebooks/unit5/ml-agents/config/ppo/SnowballTarget.yaml --env=/home/shinnigus/huggingface-deeprl/notebooks/unit5/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1720849897" }, "total": 355.01317825300794, "count": 1, "self": 0.21876014900044538, "children": { "run_training.setup": { "total": 0.024981569004012272, "count": 1, "self": 0.024981569004012272 }, "TrainerController.start_learning": { "total": 354.7694365350035, "count": 1, "self": 0.36192486407526303, "children": { "TrainerController._reset_env": { "total": 2.073350627993932, "count": 1, "self": 2.073350627993932 }, "TrainerController.advance": { "total": 352.25709309693775, "count": 18202, "self": 0.16447385840001516, "children": { "env_step": { "total": 352.09261923853774, "count": 18202, "self": 203.14512665357324, "children": { "SubprocessEnvManager._take_step": { "total": 148.77512136173027, "count": 18202, "self": 0.9593698475946439, "children": { "TorchPolicy.evaluate": { "total": 147.81575151413563, "count": 18202, "self": 147.81575151413563 } } }, "workers": { "total": 0.17237122323422227, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 354.0580552400497, "count": 18202, "is_parallel": true, "self": 204.25673208068474, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020072140032425523, "count": 1, "is_parallel": true, "self": 0.0008031540201045573, "children": { "_process_rank_one_or_two_observation": { "total": 0.001204059983137995, "count": 10, "is_parallel": true, "self": 0.001204059983137995 } } }, "UnityEnvironment.step": { "total": 0.016988370000035502, "count": 1, "is_parallel": true, "self": 0.00017563199799042195, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018049799837172031, "count": 1, "is_parallel": true, "self": 0.00018049799837172031 }, "communicator.exchange": { "total": 0.016129856012412347, "count": 1, "is_parallel": true, "self": 0.016129856012412347 }, "steps_from_proto": { "total": 0.0005023839912610129, "count": 1, "is_parallel": true, "self": 0.0001110159937525168, "children": { "_process_rank_one_or_two_observation": { "total": 0.00039136799750849605, "count": 10, "is_parallel": true, "self": 0.00039136799750849605 } } } } } } }, "UnityEnvironment.step": { "total": 149.80132315936498, "count": 18201, "is_parallel": true, "self": 3.345946033121436, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9461076494771987, "count": 18201, "is_parallel": true, "self": 1.9461076494771987 }, "communicator.exchange": { "total": 135.30271620290296, "count": 18201, "is_parallel": true, "self": 135.30271620290296 }, "steps_from_proto": { "total": 9.206553273863392, "count": 18201, "is_parallel": true, "self": 2.0330960046121618, "children": { "_process_rank_one_or_two_observation": { "total": 7.17345726925123, "count": 182010, "is_parallel": true, "self": 7.17345726925123 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011890499445144087, "count": 1, "self": 0.00011890499445144087, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 350.5575435327919, "count": 390405, "is_parallel": true, "self": 5.148553172199172, "children": { "process_trajectory": { "total": 196.51245351452962, "count": 390405, "is_parallel": true, "self": 196.0134939875279, "children": { "RLTrainer._checkpoint": { "total": 0.4989595270017162, "count": 4, "is_parallel": true, "self": 0.4989595270017162 } } }, "_update_policy": { "total": 148.8965368460631, "count": 90, "is_parallel": true, "self": 15.921343758484, "children": { "TorchPPOOptimizer.update": { "total": 132.9751930875791, "count": 4587, "is_parallel": true, "self": 132.9751930875791 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07694904100208078, "count": 1, "self": 0.0004390310059534386, "children": { "RLTrainer._checkpoint": { "total": 0.07651000999612734, "count": 1, "self": 0.07651000999612734 } } } } } } }