{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1732720136642456, "min": 1.1732720136642456, "max": 2.890307664871216, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11189.4951171875, "min": 11189.4951171875, "max": 29599.640625, "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": 9.615157127380371, "min": 0.05939009413123131, "max": 9.615157127380371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1874.95556640625, "min": 11.52167797088623, "max": 1892.8760986328125, "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.Environment.CumulativeReward.mean": { "value": 22.068181818181817, "min": 2.522727272727273, "max": 22.418181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 971.0, "min": 111.0, "max": 1233.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.068181818181817, "min": 2.522727272727273, "max": 22.418181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 971.0, "min": 111.0, "max": 1233.0, "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 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.006931638254779197, "min": 0.0022943774796052216, "max": 0.01699656923301518, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.006931638254779197, "min": 0.0022943774796052216, "max": 0.01699656923301518, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.4765321264664332, "min": 0.29741912086804706, "max": 0.9313119972745577, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4765321264664332, "min": 0.29741912086804706, "max": 0.9313119972745577, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.2960099352000083e-05, "min": 1.2960099352000083e-05, "max": 0.0018908800054560002, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.2960099352000083e-05, "min": 1.2960099352000083e-05, "max": 0.0018908800054560002, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10259200000000002, "min": 0.10259200000000002, "max": 0.478176, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10259200000000002, "min": 0.10259200000000002, "max": 0.478176, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 1.6415200000000042e-05, "min": 1.6415200000000042e-05, "max": 0.0009459856000000001, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 1.6415200000000042e-05, "min": 1.6415200000000042e-05, "max": 0.0009459856000000001, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678049538", "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 --force", "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": "1.22.4", "end_time_seconds": "1678050003" }, "total": 465.10954467600095, "count": 1, "self": 0.4311924880003062, "children": { "run_training.setup": { "total": 0.11134582600061549, "count": 1, "self": 0.11134582600061549 }, "TrainerController.start_learning": { "total": 464.56700636200003, "count": 1, "self": 0.5381371571511409, "children": { "TrainerController._reset_env": { "total": 5.962028382000426, "count": 1, "self": 5.962028382000426 }, "TrainerController.advance": { "total": 457.9087851638469, "count": 18204, "self": 0.28950167181938014, "children": { "env_step": { "total": 457.61928349202753, "count": 18204, "self": 308.31210490513877, "children": { "SubprocessEnvManager._take_step": { "total": 149.0166753590329, "count": 18204, "self": 1.6184557129563473, "children": { "TorchPolicy.evaluate": { "total": 147.39821964607654, "count": 18204, "self": 34.420324354106924, "children": { "TorchPolicy.sample_actions": { "total": 112.97789529196962, "count": 18204, "self": 112.97789529196962 } } } } }, "workers": { "total": 0.29050322785587923, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 463.13270349383856, "count": 18204, "is_parallel": true, "self": 212.74731606906062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021926450008322718, "count": 1, "is_parallel": true, "self": 0.0008525979974365328, "children": { "_process_rank_one_or_two_observation": { "total": 0.001340047003395739, "count": 10, "is_parallel": true, "self": 0.001340047003395739 } } }, "UnityEnvironment.step": { "total": 0.055703898000501795, "count": 1, "is_parallel": true, "self": 0.0005664610016538063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003252179994888138, "count": 1, "is_parallel": true, "self": 0.0003252179994888138 }, "communicator.exchange": { "total": 0.05047012199975143, "count": 1, "is_parallel": true, "self": 0.05047012199975143 }, "steps_from_proto": { "total": 0.004342096999607747, "count": 1, "is_parallel": true, "self": 0.0004848099997616373, "children": { "_process_rank_one_or_two_observation": { "total": 0.00385728699984611, "count": 10, "is_parallel": true, "self": 0.00385728699984611 } } } } } } }, "UnityEnvironment.step": { "total": 250.38538742477795, "count": 18203, "is_parallel": true, "self": 9.977922226993542, "children": { "UnityEnvironment._generate_step_input": { "total": 5.668350178797482, "count": 18203, "is_parallel": true, "self": 5.668350178797482 }, "communicator.exchange": { "total": 200.90506523594922, "count": 18203, "is_parallel": true, "self": 200.90506523594922 }, "steps_from_proto": { "total": 33.8340497830377, "count": 18203, "is_parallel": true, "self": 7.393011431790001, "children": { "_process_rank_one_or_two_observation": { "total": 26.4410383512477, "count": 182030, "is_parallel": true, "self": 26.4410383512477 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013513500016415492, "count": 1, "self": 0.00013513500016415492, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.3396579310356, "count": 589358, "is_parallel": true, "self": 15.698530454390493, "children": { "process_trajectory": { "total": 361.02739663464126, "count": 589358, "is_parallel": true, "self": 359.8065896636417, "children": { "RLTrainer._checkpoint": { "total": 1.220806970999547, "count": 4, "is_parallel": true, "self": 1.220806970999547 } } }, "_update_policy": { "total": 75.61373084200386, "count": 19, "is_parallel": true, "self": 57.87813438599005, "children": { "TorchPPOOptimizer.update": { "total": 17.73559645601381, "count": 114, "is_parallel": true, "self": 17.73559645601381 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15792052400138346, "count": 1, "self": 0.002654905001691077, "children": { "RLTrainer._checkpoint": { "total": 0.15526561899969238, "count": 1, "self": 0.15526561899969238 } } } } } } }