{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.425489902496338, "min": 1.425489902496338, "max": 2.8465843200683594, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14676.84375, "min": 13700.78515625, "max": 29057.93359375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.769600868225098, "min": 0.4487770199775696, "max": 9.769600868225098, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1992.9986572265625, "min": 87.062744140625, "max": 1992.9986572265625, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06650447859132078, "min": 0.06650447859132078, "max": 0.0777367448206539, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3325223929566039, "min": 0.2782550149485377, "max": 0.3697988536373219, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2503892842461081, "min": 0.12253868628485018, "max": 0.28144154259387183, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2519464212305407, "min": 0.4901547451394007, "max": 1.3584290713656182, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 20.163636363636364, "min": 3.522727272727273, "max": 20.163636363636364, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 155.0, "max": 1109.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 20.163636363636364, "min": 3.522727272727273, "max": 20.163636363636364, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 155.0, "max": 1109.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1774768041", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1774768269" }, "total": 227.07939782099993, "count": 1, "self": 0.43527991099972496, "children": { "run_training.setup": { "total": 0.027017496000098618, "count": 1, "self": 0.027017496000098618 }, "TrainerController.start_learning": { "total": 226.6171004140001, "count": 1, "self": 0.17776451002373506, "children": { "TrainerController._reset_env": { "total": 3.2919241290001082, "count": 1, "self": 3.2919241290001082 }, "TrainerController.advance": { "total": 223.06387828597644, "count": 9128, "self": 0.1839089709910695, "children": { "env_step": { "total": 162.73510492299147, "count": 9128, "self": 127.23260523299632, "children": { "SubprocessEnvManager._take_step": { "total": 35.39569351199725, "count": 9128, "self": 0.631435834021886, "children": { "TorchPolicy.evaluate": { "total": 34.764257677975365, "count": 9128, "self": 34.764257677975365 } } }, "workers": { "total": 0.10680617799789616, "count": 9128, "self": 0.0, "children": { "worker_root": { "total": 225.62398758202562, "count": 9128, "is_parallel": true, "self": 113.79831901401121, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004490758999963873, "count": 1, "is_parallel": true, "self": 0.0031163310000010824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013744279999627906, "count": 10, "is_parallel": true, "self": 0.0013744279999627906 } } }, "UnityEnvironment.step": { "total": 0.0686230730002535, "count": 1, "is_parallel": true, "self": 0.0005990430004203517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003969140002482163, "count": 1, "is_parallel": true, "self": 0.0003969140002482163 }, "communicator.exchange": { "total": 0.06257028099980744, "count": 1, "is_parallel": true, "self": 0.06257028099980744 }, "steps_from_proto": { "total": 0.005056834999777493, "count": 1, "is_parallel": true, "self": 0.00038068000048951944, "children": { "_process_rank_one_or_two_observation": { "total": 0.004676154999287974, "count": 10, "is_parallel": true, "self": 0.004676154999287974 } } } } } } }, "UnityEnvironment.step": { "total": 111.82566856801441, "count": 9127, "is_parallel": true, "self": 5.257819388050393, "children": { "UnityEnvironment._generate_step_input": { "total": 2.766251566988103, "count": 9127, "is_parallel": true, "self": 2.766251566988103 }, "communicator.exchange": { "total": 85.12270954498354, "count": 9127, "is_parallel": true, "self": 85.12270954498354 }, "steps_from_proto": { "total": 18.678888067992375, "count": 9127, "is_parallel": true, "self": 3.3209889340423615, "children": { "_process_rank_one_or_two_observation": { "total": 15.357899133950013, "count": 91270, "is_parallel": true, "self": 15.357899133950013 } } } } } } } } } } }, "trainer_advance": { "total": 60.144864391993906, "count": 9128, "self": 0.22591372300803414, "children": { "process_trajectory": { "total": 13.396652858984908, "count": 9128, "self": 13.173650161985279, "children": { "RLTrainer._checkpoint": { "total": 0.22300269699962882, "count": 2, "self": 0.22300269699962882 } } }, "_update_policy": { "total": 46.522297810000964, "count": 45, "self": 19.300578416979988, "children": { "TorchPPOOptimizer.update": { "total": 27.221719393020976, "count": 2292, "self": 27.221719393020976 } } } } } } }, "trainer_threads": { "total": 9.479999789618887e-07, "count": 1, "self": 9.479999789618887e-07 }, "TrainerController._save_models": { "total": 0.08353254099984042, "count": 1, "self": 0.0007359079995694628, "children": { "RLTrainer._checkpoint": { "total": 0.08279663300027096, "count": 1, "self": 0.08279663300027096 } } } } } } }