{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0300209522247314, "min": 1.0300209522247314, "max": 2.874885082244873, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9845.970703125, "min": 9845.970703125, "max": 29441.697265625, "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": 12.690324783325195, "min": 0.18491117656230927, "max": 12.690324783325195, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.61328125, "min": 35.87276840209961, "max": 2532.485595703125, "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": 0.06855923392982267, "min": 0.05947230464652954, "max": 0.07412385076263402, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2742369357192907, "min": 0.23788921858611817, "max": 0.36817526149988067, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22786833192495737, "min": 0.10627614229109467, "max": 0.2704046715123981, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9114733276998295, "min": 0.42510456916437867, "max": 1.3520233575619904, "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": 25.931818181818183, "min": 3.227272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 142.0, "max": 1358.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.227272727272727, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 142.0, "max": 1358.0, "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": "1693753705", "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": "1693754220" }, "total": 514.346608909, "count": 1, "self": 0.48494631600010507, "children": { "run_training.setup": { "total": 0.04360216700001729, "count": 1, "self": 0.04360216700001729 }, "TrainerController.start_learning": { "total": 513.8180604259999, "count": 1, "self": 0.7427928170008045, "children": { "TrainerController._reset_env": { "total": 4.205295422000006, "count": 1, "self": 4.205295422000006 }, "TrainerController.advance": { "total": 508.725743499999, "count": 18207, "self": 0.36086867699924596, "children": { "env_step": { "total": 508.36487482299975, "count": 18207, "self": 371.00844780600255, "children": { "SubprocessEnvManager._take_step": { "total": 136.99804239599302, "count": 18207, "self": 2.2125290819928978, "children": { "TorchPolicy.evaluate": { "total": 134.78551331400013, "count": 18207, "self": 134.78551331400013 } } }, "workers": { "total": 0.358384621004177, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 511.78499200600044, "count": 18207, "is_parallel": true, "self": 235.79806965399996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00742332400000123, "count": 1, "is_parallel": true, "self": 0.004883011999993414, "children": { "_process_rank_one_or_two_observation": { "total": 0.002540312000007816, "count": 10, "is_parallel": true, "self": 0.002540312000007816 } } }, "UnityEnvironment.step": { "total": 0.035436508999964644, "count": 1, "is_parallel": true, "self": 0.0006409579999626658, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003343719999975292, "count": 1, "is_parallel": true, "self": 0.0003343719999975292 }, "communicator.exchange": { "total": 0.032224183000039375, "count": 1, "is_parallel": true, "self": 0.032224183000039375 }, "steps_from_proto": { "total": 0.0022369959999650746, "count": 1, "is_parallel": true, "self": 0.00040350699993041417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018334890000346604, "count": 10, "is_parallel": true, "self": 0.0018334890000346604 } } } } } } }, "UnityEnvironment.step": { "total": 275.9869223520005, "count": 18206, "is_parallel": true, "self": 11.8591132899939, "children": { "UnityEnvironment._generate_step_input": { "total": 5.938266308994855, "count": 18206, "is_parallel": true, "self": 5.938266308994855 }, "communicator.exchange": { "total": 219.39059850600387, "count": 18206, "is_parallel": true, "self": 219.39059850600387 }, "steps_from_proto": { "total": 38.79894424700785, "count": 18206, "is_parallel": true, "self": 7.481159825982161, "children": { "_process_rank_one_or_two_observation": { "total": 31.317784421025692, "count": 182060, "is_parallel": true, "self": 31.317784421025692 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001919759999964299, "count": 1, "self": 0.0001919759999964299, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 505.11083814004525, "count": 484730, "is_parallel": true, "self": 10.583925903048168, "children": { "process_trajectory": { "total": 281.903168613997, "count": 484730, "is_parallel": true, "self": 280.38602749199714, "children": { "RLTrainer._checkpoint": { "total": 1.5171411219998845, "count": 4, "is_parallel": true, "self": 1.5171411219998845 } } }, "_update_policy": { "total": 212.62374362300005, "count": 90, "is_parallel": true, "self": 79.08769878700446, "children": { "TorchPPOOptimizer.update": { "total": 133.5360448359956, "count": 4587, "is_parallel": true, "self": 133.5360448359956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14403671100001247, "count": 1, "self": 0.001051034000056461, "children": { "RLTrainer._checkpoint": { "total": 0.142985676999956, "count": 1, "self": 0.142985676999956 } } } } } } }