{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.1271471977233887, "min": 2.1271471977233887, "max": 2.888671398162842, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 21830.912109375, "min": 20836.951171875, "max": 29582.884765625, "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": 5.495637893676758, "min": 0.3136531412601471, "max": 5.495637893676758, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1121.110107421875, "min": 60.84870910644531, "max": 1121.110107421875, "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.Losses.PolicyLoss.mean": { "value": 0.06947156742580951, "min": 0.06266162015508955, "max": 0.06947156742580951, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34735783712904755, "min": 0.2506464806203582, "max": 0.34735783712904755, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.4210761183617161, "min": 0.1549305331381951, "max": 0.4761880072308522, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 2.1053805918085806, "min": 0.6197221325527804, "max": 2.1053805918085806, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.488094512e-06, "min": 5.488094512e-06, "max": 9.458800541200001e-05, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.744047256e-05, "min": 2.744047256e-05, "max": 0.00042344007656, "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.CumulativeReward.mean": { "value": 11.218181818181819, "min": 2.659090909090909, "max": 11.218181818181819, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 617.0, "min": 117.0, "max": 617.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 11.218181818181819, "min": 2.659090909090909, "max": 11.218181818181819, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 617.0, "min": 117.0, "max": 617.0, "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": "1703716623", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./content/ml-agents/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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703716845" }, "total": 222.30921071400007, "count": 1, "self": 0.4425772310000866, "children": { "run_training.setup": { "total": 0.0558678620000137, "count": 1, "self": 0.0558678620000137 }, "TrainerController.start_learning": { "total": 221.81076562099997, "count": 1, "self": 0.3012840320120631, "children": { "TrainerController._reset_env": { "total": 3.1971039109998856, "count": 1, "self": 3.1971039109998856 }, "TrainerController.advance": { "total": 218.20957977698845, "count": 9133, "self": 0.13008575497406127, "children": { "env_step": { "total": 218.0794940220144, "count": 9133, "self": 143.2865913740261, "children": { "SubprocessEnvManager._take_step": { "total": 74.65171065899858, "count": 9133, "self": 0.7194718640034807, "children": { "TorchPolicy.evaluate": { "total": 73.9322387949951, "count": 9133, "self": 73.9322387949951 } } }, "workers": { "total": 0.14119198898970353, "count": 9133, "self": 0.0, "children": { "worker_root": { "total": 221.12698380197298, "count": 9133, "is_parallel": true, "self": 110.68862474698608, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004351200999735738, "count": 1, "is_parallel": true, "self": 0.003000376999807486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013508239999282523, "count": 10, "is_parallel": true, "self": 0.0013508239999282523 } } }, "UnityEnvironment.step": { "total": 0.07312200300020777, "count": 1, "is_parallel": true, "self": 0.0006115020000834193, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003762879996429547, "count": 1, "is_parallel": true, "self": 0.0003762879996429547 }, "communicator.exchange": { "total": 0.07021586500013655, "count": 1, "is_parallel": true, "self": 0.07021586500013655 }, "steps_from_proto": { "total": 0.0019183480003448494, "count": 1, "is_parallel": true, "self": 0.00038209100011954433, "children": { "_process_rank_one_or_two_observation": { "total": 0.001536257000225305, "count": 10, "is_parallel": true, "self": 0.001536257000225305 } } } } } } }, "UnityEnvironment.step": { "total": 110.4383590549869, "count": 9132, "is_parallel": true, "self": 5.267941038971003, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6074433330136344, "count": 9132, "is_parallel": true, "self": 2.6074433330136344 }, "communicator.exchange": { "total": 85.9824507029798, "count": 9132, "is_parallel": true, "self": 85.9824507029798 }, "steps_from_proto": { "total": 16.580523980022463, "count": 9132, "is_parallel": true, "self": 3.1630494271198586, "children": { "_process_rank_one_or_two_observation": { "total": 13.417474552902604, "count": 91320, "is_parallel": true, "self": 13.417474552902604 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00038994399983494077, "count": 1, "self": 0.00038994399983494077, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 215.52911954902493, "count": 335398, "is_parallel": true, "self": 6.762086083188478, "children": { "process_trajectory": { "total": 119.84873475283621, "count": 335398, "is_parallel": true, "self": 119.15994499883618, "children": { "RLTrainer._checkpoint": { "total": 0.6887897540000267, "count": 2, "is_parallel": true, "self": 0.6887897540000267 } } }, "_update_policy": { "total": 88.91829871300024, "count": 45, "is_parallel": true, "self": 27.598422838996157, "children": { "TorchPPOOptimizer.update": { "total": 61.31987587400408, "count": 2289, "is_parallel": true, "self": 61.31987587400408 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10240795699974115, "count": 1, "self": 0.000980067999989842, "children": { "RLTrainer._checkpoint": { "total": 0.1014278889997513, "count": 1, "self": 0.1014278889997513 } } } } } } }