{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7075469493865967, "min": 1.7075469493865967, "max": 2.8718860149383545, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17486.98828125, "min": 17128.03125, "max": 29442.576171875, "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": 9.08544635772705, "min": 0.2940658926963806, "max": 9.08544635772705, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1853.43115234375, "min": 57.04878234863281, "max": 1853.43115234375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06652085697606511, "min": 0.06085493482148828, "max": 0.07853022093460073, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33260428488032556, "min": 0.24341973928595312, "max": 0.35824057095377093, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.27105463462717394, "min": 0.11490086922718795, "max": 0.2726640262440139, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3552731731358696, "min": 0.4596034769087518, "max": 1.3633201312200696, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "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": 19.490909090909092, "min": 3.4318181818181817, "max": 19.490909090909092, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1072.0, "min": 151.0, "max": 1072.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.490909090909092, "min": 3.4318181818181817, "max": 19.490909090909092, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1072.0, "min": 151.0, "max": 1072.0, "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": "1716115921", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716116234" }, "total": 313.00819820899994, "count": 1, "self": 0.6507097009999825, "children": { "run_training.setup": { "total": 0.07402426900000592, "count": 1, "self": 0.07402426900000592 }, "TrainerController.start_learning": { "total": 312.28346423899995, "count": 1, "self": 0.7972583400098756, "children": { "TrainerController._reset_env": { "total": 4.141600967000045, "count": 1, "self": 4.141600967000045 }, "TrainerController.advance": { "total": 307.22816979399, "count": 9135, "self": 0.22386033798909466, "children": { "env_step": { "total": 307.0043094560009, "count": 9135, "self": 235.53236298799072, "children": { "SubprocessEnvManager._take_step": { "total": 71.25388873699774, "count": 9135, "self": 1.3071070909990112, "children": { "TorchPolicy.evaluate": { "total": 69.94678164599873, "count": 9135, "self": 69.94678164599873 } } }, "workers": { "total": 0.2180577310124363, "count": 9135, "self": 0.0, "children": { "worker_root": { "total": 310.8626557329991, "count": 9135, "is_parallel": true, "self": 147.69347845899802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008673594000015328, "count": 1, "is_parallel": true, "self": 0.0046821349999390804, "children": { "_process_rank_one_or_two_observation": { "total": 0.003991459000076247, "count": 10, "is_parallel": true, "self": 0.003991459000076247 } } }, "UnityEnvironment.step": { "total": 0.04667586600010054, "count": 1, "is_parallel": true, "self": 0.0008145270001023164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047266499996112543, "count": 1, "is_parallel": true, "self": 0.00047266499996112543 }, "communicator.exchange": { "total": 0.04294306899998901, "count": 1, "is_parallel": true, "self": 0.04294306899998901 }, "steps_from_proto": { "total": 0.00244560500004809, "count": 1, "is_parallel": true, "self": 0.00047981900013382983, "children": { "_process_rank_one_or_two_observation": { "total": 0.00196578599991426, "count": 10, "is_parallel": true, "self": 0.00196578599991426 } } } } } } }, "UnityEnvironment.step": { "total": 163.16917727400107, "count": 9134, "is_parallel": true, "self": 7.721400475030691, "children": { "UnityEnvironment._generate_step_input": { "total": 3.927587473985227, "count": 9134, "is_parallel": true, "self": 3.927587473985227 }, "communicator.exchange": { "total": 128.59942833099, "count": 9134, "is_parallel": true, "self": 128.59942833099 }, "steps_from_proto": { "total": 22.920760993995145, "count": 9134, "is_parallel": true, "self": 4.621585600948606, "children": { "_process_rank_one_or_two_observation": { "total": 18.29917539304654, "count": 91340, "is_parallel": true, "self": 18.29917539304654 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0005160260000138805, "count": 1, "self": 0.0005160260000138805, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 303.79662841900847, "count": 401850, "is_parallel": true, "self": 9.484850194998558, "children": { "process_trajectory": { "total": 167.71816147101083, "count": 401850, "is_parallel": true, "self": 167.36281561001078, "children": { "RLTrainer._checkpoint": { "total": 0.35534586100004617, "count": 2, "is_parallel": true, "self": 0.35534586100004617 } } }, "_update_policy": { "total": 126.59361675299908, "count": 45, "is_parallel": true, "self": 33.52767215099789, "children": { "TorchPPOOptimizer.update": { "total": 93.0659446020012, "count": 2292, "is_parallel": true, "self": 93.0659446020012 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11591911200002869, "count": 1, "self": 0.0015577140000004874, "children": { "RLTrainer._checkpoint": { "total": 0.1143613980000282, "count": 1, "self": 0.1143613980000282 } } } } } } }