{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0385013818740845, "min": 1.03290855884552, "max": 2.8758580684661865, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9927.03515625, "min": 9927.03515625, "max": 29483.296875, "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": 12.885482788085938, "min": 0.42007559537887573, "max": 12.885482788085938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.669189453125, "min": 81.49466705322266, "max": 2578.7421875, "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": 0.06997200378317953, "min": 0.06278613742552788, "max": 0.07147457014670021, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2798880151327181, "min": 0.25114454970211153, "max": 0.35737285073350106, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22350715049633793, "min": 0.09541951100839594, "max": 0.2842084803417617, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8940286019853517, "min": 0.38167804403358374, "max": 1.3718428769532371, "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": 25.59090909090909, "min": 2.6818181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 118.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 2.6818181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 118.0, "max": 1418.0, "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": "1693866551", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693867027" }, "total": 475.26740320700003, "count": 1, "self": 0.8668496220000179, "children": { "run_training.setup": { "total": 0.04282209200005127, "count": 1, "self": 0.04282209200005127 }, "TrainerController.start_learning": { "total": 474.35773149299996, "count": 1, "self": 0.5527197620076549, "children": { "TrainerController._reset_env": { "total": 3.991729894000059, "count": 1, "self": 3.991729894000059 }, "TrainerController.advance": { "total": 469.5709128729925, "count": 18213, "self": 0.2684448169962934, "children": { "env_step": { "total": 469.3024680559962, "count": 18213, "self": 340.6232156200027, "children": { "SubprocessEnvManager._take_step": { "total": 128.3963891830016, "count": 18213, "self": 1.7542979100006733, "children": { "TorchPolicy.evaluate": { "total": 126.64209127300091, "count": 18213, "self": 126.64209127300091 } } }, "workers": { "total": 0.28286325299188775, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 472.68669917399995, "count": 18213, "is_parallel": true, "self": 221.55366312900173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005423597999993035, "count": 1, "is_parallel": true, "self": 0.003917111000077966, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015064869999150687, "count": 10, "is_parallel": true, "self": 0.0015064869999150687 } } }, "UnityEnvironment.step": { "total": 0.03605460400001448, "count": 1, "is_parallel": true, "self": 0.0005900390001443157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000314887999934399, "count": 1, "is_parallel": true, "self": 0.000314887999934399 }, "communicator.exchange": { "total": 0.032846744999915245, "count": 1, "is_parallel": true, "self": 0.032846744999915245 }, "steps_from_proto": { "total": 0.002302932000020519, "count": 1, "is_parallel": true, "self": 0.00040000600006351306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019029259999570058, "count": 10, "is_parallel": true, "self": 0.0019029259999570058 } } } } } } }, "UnityEnvironment.step": { "total": 251.13303604499822, "count": 18212, "is_parallel": true, "self": 10.57543304400258, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4817674099936085, "count": 18212, "is_parallel": true, "self": 5.4817674099936085 }, "communicator.exchange": { "total": 197.49462878600457, "count": 18212, "is_parallel": true, "self": 197.49462878600457 }, "steps_from_proto": { "total": 37.581206804997464, "count": 18212, "is_parallel": true, "self": 6.758345527012693, "children": { "_process_rank_one_or_two_observation": { "total": 30.82286127798477, "count": 182120, "is_parallel": true, "self": 30.82286127798477 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001124839998283278, "count": 1, "self": 0.0001124839998283278, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.96546186390583, "count": 451354, "is_parallel": true, "self": 9.705479383879265, "children": { "process_trajectory": { "total": 256.60624268802644, "count": 451354, "is_parallel": true, "self": 255.0308911880262, "children": { "RLTrainer._checkpoint": { "total": 1.575351500000238, "count": 4, "is_parallel": true, "self": 1.575351500000238 } } }, "_update_policy": { "total": 199.65373979200012, "count": 90, "is_parallel": true, "self": 78.94537650299844, "children": { "TorchPPOOptimizer.update": { "total": 120.70836328900168, "count": 4587, "is_parallel": true, "self": 120.70836328900168 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2422564799999236, "count": 1, "self": 0.0012525310000910395, "children": { "RLTrainer._checkpoint": { "total": 0.24100394899983257, "count": 1, "self": 0.24100394899983257 } } } } } } }