{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.207751989364624, "min": 1.207751989364624, "max": 2.890331745147705, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12302.162109375, "min": 11659.7587890625, "max": 29568.09375, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.79448413848877, "min": -0.07552412152290344, "max": 11.79448413848877, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2299.92431640625, "min": -14.651679992675781, "max": 2386.53369140625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.295454545454547, "min": 2.727272727272727, "max": 25.40909090909091, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 120.0, "max": 1369.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 2.727272727272727, "max": 25.40909090909091, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 120.0, "max": 1369.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06782420906771829, "min": 0.06177909223305657, "max": 0.07829875268829103, "count": 38 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06782420906771829, "min": 0.06177909223305657, "max": 0.07829875268829103, "count": 38 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1718453077909847, "min": 0.08486949935847637, "max": 0.28887098642687004, "count": 38 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1718453077909847, "min": 0.08486949935847637, "max": 0.28887098642687004, "count": 38 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.944099352000012e-06, "min": 1.944099352000012e-06, "max": 0.0002918160027279999, "count": 38 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.944099352000012e-06, "min": 1.944099352000012e-06, "max": 0.0002918160027279999, "count": 38 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10064800000000006, "min": 0.10064800000000006, "max": 0.19727199999999998, "count": 38 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10064800000000006, "min": 0.10064800000000006, "max": 0.19727199999999998, "count": 38 }, "SnowballTarget.Policy.Beta.mean": { "value": 4.23352000000002e-05, "min": 4.23352000000002e-05, "max": 0.004863872800000001, "count": 38 }, "SnowballTarget.Policy.Beta.sum": { "value": 4.23352000000002e-05, "min": 4.23352000000002e-05, "max": 0.004863872800000001, "count": 38 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674390195", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674391069" }, "total": 873.6373618940002, "count": 1, "self": 0.3963074379998943, "children": { "run_training.setup": { "total": 0.10794372999998814, "count": 1, "self": 0.10794372999998814 }, "TrainerController.start_learning": { "total": 873.1331107260003, "count": 1, "self": 0.9734170389501742, "children": { "TrainerController._reset_env": { "total": 9.53833413700022, "count": 1, "self": 9.53833413700022 }, "TrainerController.advance": { "total": 862.4823449430496, "count": 36404, "self": 0.5009638840228945, "children": { "env_step": { "total": 861.9813810590267, "count": 36404, "self": 620.0772408260518, "children": { "SubprocessEnvManager._take_step": { "total": 241.39179776993888, "count": 36404, "self": 2.676966732983601, "children": { "TorchPolicy.evaluate": { "total": 238.71483103695527, "count": 36404, "self": 53.81133948596607, "children": { "TorchPolicy.sample_actions": { "total": 184.9034915509892, "count": 36404, "self": 184.9034915509892 } } } } }, "workers": { "total": 0.5123424630360205, "count": 36404, "self": 0.0, "children": { "worker_root": { "total": 870.9634404749781, "count": 36404, "is_parallel": true, "self": 426.72411195695304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061252860000422515, "count": 1, "is_parallel": true, "self": 0.0036440129997572512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024812730002850003, "count": 10, "is_parallel": true, "self": 0.0024812730002850003 } } }, "UnityEnvironment.step": { "total": 0.034976508999989164, "count": 1, "is_parallel": true, "self": 0.0003470140004537825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003639749998001207, "count": 1, "is_parallel": true, "self": 0.0003639749998001207 }, "communicator.exchange": { "total": 0.032471825999891735, "count": 1, "is_parallel": true, "self": 0.032471825999891735 }, "steps_from_proto": { "total": 0.0017936939998435264, "count": 1, "is_parallel": true, "self": 0.00039677400036453037, "children": { "_process_rank_one_or_two_observation": { "total": 0.001396919999478996, "count": 10, "is_parallel": true, "self": 0.001396919999478996 } } } } } } }, "UnityEnvironment.step": { "total": 444.2393285180251, "count": 36403, "is_parallel": true, "self": 16.292579570043472, "children": { "UnityEnvironment._generate_step_input": { "total": 9.899071725977137, "count": 36403, "is_parallel": true, "self": 9.899071725977137 }, "communicator.exchange": { "total": 358.14114628500874, "count": 36403, "is_parallel": true, "self": 358.14114628500874 }, "steps_from_proto": { "total": 59.90653093699575, "count": 36403, "is_parallel": true, "self": 12.731110507022095, "children": { "_process_rank_one_or_two_observation": { "total": 47.175420429973656, "count": 364030, "is_parallel": true, "self": 47.175420429973656 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.004600032203598e-05, "count": 1, "self": 4.004600032203598e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 853.8388547338154, "count": 930275, "is_parallel": true, "self": 25.174375027753285, "children": { "process_trajectory": { "total": 623.4558495450624, "count": 930275, "is_parallel": true, "self": 621.5566202950627, "children": { "RLTrainer._checkpoint": { "total": 1.8992292499997347, "count": 8, "is_parallel": true, "self": 1.8992292499997347 } } }, "_update_policy": { "total": 205.20863016099975, "count": 38, "is_parallel": true, "self": 79.72471706498573, "children": { "TorchPPOOptimizer.update": { "total": 125.48391309601402, "count": 9270, "is_parallel": true, "self": 125.48391309601402 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13897456099994088, "count": 1, "self": 0.0016046770001594268, "children": { "RLTrainer._checkpoint": { "total": 0.13736988399978145, "count": 1, "self": 0.13736988399978145 } } } } } } }