{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7883507609367371, "min": 0.7883507609367371, "max": 2.8738811016082764, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7561.8603515625, "min": 7561.8603515625, "max": 29526.25390625, "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": 12.996211051940918, "min": 0.2577475309371948, "max": 12.996211051940918, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2534.26123046875, "min": 50.003021240234375, "max": 2645.0625, "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": 0.06989642114472101, "min": 0.061533780614434576, "max": 0.0777204619810743, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27958568457888405, "min": 0.2461351224577383, "max": 0.3615940351737663, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1872509928310619, "min": 0.10276488784938029, "max": 0.26974370064688663, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7490039713242476, "min": 0.41105955139752115, "max": 1.348718503234433, "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": 25.454545454545453, "min": 3.022727272727273, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 133.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.022727272727273, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 133.0, "max": 1400.0, "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": "1675610817", "python_version": "3.10.4 (main, Feb 5 2023, 16:54:05) [GCC 12.2.0]", "command_line_arguments": "/home/ash/ak/code/Courses/RL/hugging_face/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675611168" }, "total": 350.8939326119944, "count": 1, "self": 0.27065492999827256, "children": { "run_training.setup": { "total": 0.020594925998011604, "count": 1, "self": 0.020594925998011604 }, "TrainerController.start_learning": { "total": 350.6026827559981, "count": 1, "self": 0.4724938456492964, "children": { "TrainerController._reset_env": { "total": 3.092906905003474, "count": 1, "self": 3.092906905003474 }, "TrainerController.advance": { "total": 346.9285684993447, "count": 18206, "self": 0.24283364262373652, "children": { "env_step": { "total": 346.68573485672096, "count": 18206, "self": 252.42335820887092, "children": { "SubprocessEnvManager._take_step": { "total": 94.00843801227165, "count": 18206, "self": 1.2415540480287746, "children": { "TorchPolicy.evaluate": { "total": 92.76688396424288, "count": 18206, "self": 92.76688396424288 } } }, "workers": { "total": 0.25393863557837903, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 349.97738286581443, "count": 18206, "is_parallel": true, "self": 183.6330502773053, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015517079955316149, "count": 1, "is_parallel": true, "self": 0.0005038059971411712, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010479019983904436, "count": 10, "is_parallel": true, "self": 0.0010479019983904436 } } }, "UnityEnvironment.step": { "total": 0.030766636002226733, "count": 1, "is_parallel": true, "self": 0.00062792599783279, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004250089987181127, "count": 1, "is_parallel": true, "self": 0.0004250089987181127 }, "communicator.exchange": { "total": 0.027227089005464222, "count": 1, "is_parallel": true, "self": 0.027227089005464222 }, "steps_from_proto": { "total": 0.0024866120002116077, "count": 1, "is_parallel": true, "self": 0.00037349799822550267, "children": { "_process_rank_one_or_two_observation": { "total": 0.002113114001986105, "count": 10, "is_parallel": true, "self": 0.002113114001986105 } } } } } } }, "UnityEnvironment.step": { "total": 166.34433258850913, "count": 18205, "is_parallel": true, "self": 8.045762701331114, "children": { "UnityEnvironment._generate_step_input": { "total": 4.209461102516798, "count": 18205, "is_parallel": true, "self": 4.209461102516798 }, "communicator.exchange": { "total": 127.46449394080992, "count": 18205, "is_parallel": true, "self": 127.46449394080992 }, "steps_from_proto": { "total": 26.624614843851305, "count": 18205, "is_parallel": true, "self": 5.246420289062371, "children": { "_process_rank_one_or_two_observation": { "total": 21.378194554788934, "count": 182050, "is_parallel": true, "self": 21.378194554788934 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.489600440952927e-05, "count": 1, "self": 8.489600440952927e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 346.0045031357731, "count": 175403, "is_parallel": true, "self": 3.083280578284757, "children": { "process_trajectory": { "total": 190.16999289850355, "count": 175403, "is_parallel": true, "self": 189.4802967345022, "children": { "RLTrainer._checkpoint": { "total": 0.6896961640013615, "count": 4, "is_parallel": true, "self": 0.6896961640013615 } } }, "_update_policy": { "total": 152.7512296589848, "count": 90, "is_parallel": true, "self": 48.96175902758114, "children": { "TorchPPOOptimizer.update": { "total": 103.78947063140367, "count": 4587, "is_parallel": true, "self": 103.78947063140367 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10862860999623081, "count": 1, "self": 0.0006953650008654222, "children": { "RLTrainer._checkpoint": { "total": 0.10793324499536538, "count": 1, "self": 0.10793324499536538 } } } } } } }