{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9472848176956177, "min": 0.9472848176956177, "max": 2.869218111038208, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9055.095703125, "min": 9055.095703125, "max": 29478.34765625, "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": 12.911767959594727, "min": 0.3344009220600128, "max": 12.911767959594727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.794677734375, "min": 64.873779296875, "max": 2619.83203125, "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": 0.06826849919875089, "min": 0.06285257132749036, "max": 0.07591896645916515, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27307399679500355, "min": 0.26349316968516373, "max": 0.3795948322958258, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20888341473890285, "min": 0.10543559432285382, "max": 0.2835400447103323, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8355336589556114, "min": 0.4217423772914153, "max": 1.3432362617230884, "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": 3.1363636363636362, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 138.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.1363636363636362, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 138.0, "max": 1392.0, "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": "1693774212", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693774714" }, "total": 501.82014499200005, "count": 1, "self": 0.4359538850001172, "children": { "run_training.setup": { "total": 0.07343721799998093, "count": 1, "self": 0.07343721799998093 }, "TrainerController.start_learning": { "total": 501.31075388899995, "count": 1, "self": 0.6517777109981466, "children": { "TrainerController._reset_env": { "total": 4.718465925999965, "count": 1, "self": 4.718465925999965 }, "TrainerController.advance": { "total": 495.79148506100177, "count": 18201, "self": 0.330216970999345, "children": { "env_step": { "total": 495.4612680900024, "count": 18201, "self": 360.39600151600564, "children": { "SubprocessEnvManager._take_step": { "total": 134.7451867449924, "count": 18201, "self": 1.9058014079932377, "children": { "TorchPolicy.evaluate": { "total": 132.83938533699916, "count": 18201, "self": 132.83938533699916 } } }, "workers": { "total": 0.3200798290043849, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 499.56081022199163, "count": 18201, "is_parallel": true, "self": 233.2932756730014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006977345999985118, "count": 1, "is_parallel": true, "self": 0.004373436999912883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026039090000722354, "count": 10, "is_parallel": true, "self": 0.0026039090000722354 } } }, "UnityEnvironment.step": { "total": 0.04782032299999628, "count": 1, "is_parallel": true, "self": 0.00047088199988820634, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004247870000426701, "count": 1, "is_parallel": true, "self": 0.0004247870000426701 }, "communicator.exchange": { "total": 0.04454135100002077, "count": 1, "is_parallel": true, "self": 0.04454135100002077 }, "steps_from_proto": { "total": 0.0023833030000446342, "count": 1, "is_parallel": true, "self": 0.0004175039999836372, "children": { "_process_rank_one_or_two_observation": { "total": 0.001965799000060997, "count": 10, "is_parallel": true, "self": 0.001965799000060997 } } } } } } }, "UnityEnvironment.step": { "total": 266.2675345489902, "count": 18200, "is_parallel": true, "self": 11.217005711983745, "children": { "UnityEnvironment._generate_step_input": { "total": 5.597600945004331, "count": 18200, "is_parallel": true, "self": 5.597600945004331 }, "communicator.exchange": { "total": 210.8846044629961, "count": 18200, "is_parallel": true, "self": 210.8846044629961 }, "steps_from_proto": { "total": 38.56832342900606, "count": 18200, "is_parallel": true, "self": 7.13945212497913, "children": { "_process_rank_one_or_two_observation": { "total": 31.428871304026927, "count": 182000, "is_parallel": true, "self": 31.428871304026927 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013712800000575953, "count": 1, "self": 0.00013712800000575953, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 492.12946998303835, "count": 454484, "is_parallel": true, "self": 10.424712083070517, "children": { "process_trajectory": { "total": 268.917172444968, "count": 454484, "is_parallel": true, "self": 268.1551442449679, "children": { "RLTrainer._checkpoint": { "total": 0.7620282000000884, "count": 4, "is_parallel": true, "self": 0.7620282000000884 } } }, "_update_policy": { "total": 212.78758545499983, "count": 90, "is_parallel": true, "self": 81.53417154900029, "children": { "TorchPPOOptimizer.update": { "total": 131.25341390599954, "count": 4587, "is_parallel": true, "self": 131.25341390599954 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14888806300007218, "count": 1, "self": 0.0009790030001113337, "children": { "RLTrainer._checkpoint": { "total": 0.14790905999996085, "count": 1, "self": 0.14790905999996085 } } } } } } }