{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9093418121337891, "min": 0.9093418121337891, "max": 2.86033034324646, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8682.3955078125, "min": 8682.3955078125, "max": 29324.10546875, "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": 13.090479850769043, "min": 0.3983933627605438, "max": 13.09923267364502, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2552.6435546875, "min": 77.28831481933594, "max": 2672.243408203125, "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": 0.07513779475623011, "min": 0.06412339530880654, "max": 0.07513779475623011, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30055117902492046, "min": 0.2566547146591035, "max": 0.3528568777187234, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2082226380121474, "min": 0.13545278966079888, "max": 0.29475106613016594, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8328905520485896, "min": 0.5418111586431955, "max": 1.281653469976257, "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": 25.772727272727273, "min": 3.6136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 159.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.6136363636363638, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 159.0, "max": 1411.0, "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": "1699465774", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699466262" }, "total": 487.837070324, "count": 1, "self": 0.6257057519999307, "children": { "run_training.setup": { "total": 0.04524966700000732, "count": 1, "self": 0.04524966700000732 }, "TrainerController.start_learning": { "total": 487.1661149050001, "count": 1, "self": 0.5723290340058611, "children": { "TrainerController._reset_env": { "total": 8.936233082999934, "count": 1, "self": 8.936233082999934 }, "TrainerController.advance": { "total": 477.52611315399395, "count": 18208, "self": 0.2868792400101938, "children": { "env_step": { "total": 477.23923391398375, "count": 18208, "self": 325.0977740189785, "children": { "SubprocessEnvManager._take_step": { "total": 151.85485643299012, "count": 18208, "self": 1.4802175569943756, "children": { "TorchPolicy.evaluate": { "total": 150.37463887599574, "count": 18208, "self": 150.37463887599574 } } }, "workers": { "total": 0.28660346201513676, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 485.7782792280109, "count": 18208, "is_parallel": true, "self": 238.7398140599953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005754633000151443, "count": 1, "is_parallel": true, "self": 0.004118777000485352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016358559996660915, "count": 10, "is_parallel": true, "self": 0.0016358559996660915 } } }, "UnityEnvironment.step": { "total": 0.049131866999914564, "count": 1, "is_parallel": true, "self": 0.0004013249997569801, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033645999997133913, "count": 1, "is_parallel": true, "self": 0.00033645999997133913 }, "communicator.exchange": { "total": 0.04638985500014314, "count": 1, "is_parallel": true, "self": 0.04638985500014314 }, "steps_from_proto": { "total": 0.0020042270000431017, "count": 1, "is_parallel": true, "self": 0.00038817300014670764, "children": { "_process_rank_one_or_two_observation": { "total": 0.001616053999896394, "count": 10, "is_parallel": true, "self": 0.001616053999896394 } } } } } } }, "UnityEnvironment.step": { "total": 247.0384651680156, "count": 18207, "is_parallel": true, "self": 11.009798440040413, "children": { "UnityEnvironment._generate_step_input": { "total": 5.777832974006742, "count": 18207, "is_parallel": true, "self": 5.777832974006742 }, "communicator.exchange": { "total": 193.57518318697635, "count": 18207, "is_parallel": true, "self": 193.57518318697635 }, "steps_from_proto": { "total": 36.67565056699209, "count": 18207, "is_parallel": true, "self": 6.8479993730427395, "children": { "_process_rank_one_or_two_observation": { "total": 29.82765119394935, "count": 182070, "is_parallel": true, "self": 29.82765119394935 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021123800024724915, "count": 1, "self": 0.00021123800024724915, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.3334777978878, "count": 504188, "is_parallel": true, "self": 11.102065914960122, "children": { "process_trajectory": { "total": 270.41277739492944, "count": 504188, "is_parallel": true, "self": 269.46059938092935, "children": { "RLTrainer._checkpoint": { "total": 0.9521780140000828, "count": 4, "is_parallel": true, "self": 0.9521780140000828 } } }, "_update_policy": { "total": 191.81863448799822, "count": 90, "is_parallel": true, "self": 59.46327046599731, "children": { "TorchPPOOptimizer.update": { "total": 132.3553640220009, "count": 4587, "is_parallel": true, "self": 132.3553640220009 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13122839600009684, "count": 1, "self": 0.0011053060002268467, "children": { "RLTrainer._checkpoint": { "total": 0.13012308999987, "count": 1, "self": 0.13012308999987 } } } } } } }