{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0302633047103882, "min": 1.0302633047103882, "max": 2.8710601329803467, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9882.28515625, "min": 9882.28515625, "max": 29402.52734375, "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": 11.659948348999023, "min": 0.3112582266330719, "max": 11.659948348999023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2273.68994140625, "min": 60.384098052978516, "max": 2350.47998046875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07275105488477886, "min": 0.0636507067277967, "max": 0.07483793631168631, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2910042195391154, "min": 0.2546028269111868, "max": 0.3741896815584315, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18833267725273672, "min": 0.11867392266468219, "max": 0.26831841863253536, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7533307090109469, "min": 0.47469569065872874, "max": 1.2724559277880425, "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": 23.113636363636363, "min": 3.3181818181818183, "max": 23.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1017.0, "min": 146.0, "max": 1269.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.113636363636363, "min": 3.3181818181818183, "max": 23.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1017.0, "min": 146.0, "max": 1269.0, "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": "1683515975", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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", "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": "1683516638" }, "total": 662.3333466660001, "count": 1, "self": 0.5983253940001987, "children": { "run_training.setup": { "total": 0.07953311699998267, "count": 1, "self": 0.07953311699998267 }, "TrainerController.start_learning": { "total": 661.655488155, "count": 1, "self": 0.9327151700017566, "children": { "TrainerController._reset_env": { "total": 1.4971869349999452, "count": 1, "self": 1.4971869349999452 }, "TrainerController.advance": { "total": 659.0448864089982, "count": 18213, "self": 0.45356744900755075, "children": { "env_step": { "total": 658.5913189599906, "count": 18213, "self": 532.6519415020052, "children": { "SubprocessEnvManager._take_step": { "total": 125.49238298798923, "count": 18213, "self": 3.448137453002687, "children": { "TorchPolicy.evaluate": { "total": 122.04424553498654, "count": 18213, "self": 122.04424553498654 } } }, "workers": { "total": 0.4469944699961843, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 658.9533007590029, "count": 18213, "is_parallel": true, "self": 280.1256840959935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007951534000085303, "count": 1, "is_parallel": true, "self": 0.005025827000281424, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029257069998038787, "count": 10, "is_parallel": true, "self": 0.0029257069998038787 } } }, "UnityEnvironment.step": { "total": 0.15132909700002983, "count": 1, "is_parallel": true, "self": 0.0012750690000302711, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046733199997106567, "count": 1, "is_parallel": true, "self": 0.00046733199997106567 }, "communicator.exchange": { "total": 0.14316306900002473, "count": 1, "is_parallel": true, "self": 0.14316306900002473 }, "steps_from_proto": { "total": 0.006423627000003762, "count": 1, "is_parallel": true, "self": 0.0005106089998889729, "children": { "_process_rank_one_or_two_observation": { "total": 0.005913018000114789, "count": 10, "is_parallel": true, "self": 0.005913018000114789 } } } } } } }, "UnityEnvironment.step": { "total": 378.8276166630094, "count": 18212, "is_parallel": true, "self": 16.315727135003044, "children": { "UnityEnvironment._generate_step_input": { "total": 8.359657818996766, "count": 18212, "is_parallel": true, "self": 8.359657818996766 }, "communicator.exchange": { "total": 302.3829950259985, "count": 18212, "is_parallel": true, "self": 302.3829950259985 }, "steps_from_proto": { "total": 51.76923668301106, "count": 18212, "is_parallel": true, "self": 10.250892495004223, "children": { "_process_rank_one_or_two_observation": { "total": 41.518344188006836, "count": 182120, "is_parallel": true, "self": 41.518344188006836 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025654700016275456, "count": 1, "self": 0.00025654700016275456, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 652.7570968870765, "count": 688591, "is_parallel": true, "self": 17.426853781145837, "children": { "process_trajectory": { "total": 355.41083776093024, "count": 688591, "is_parallel": true, "self": 353.9716955949301, "children": { "RLTrainer._checkpoint": { "total": 1.4391421660001242, "count": 4, "is_parallel": true, "self": 1.4391421660001242 } } }, "_update_policy": { "total": 279.9194053450004, "count": 90, "is_parallel": true, "self": 98.17866854000454, "children": { "TorchPPOOptimizer.update": { "total": 181.7407368049959, "count": 4587, "is_parallel": true, "self": 181.7407368049959 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18044309399988379, "count": 1, "self": 0.0015354979998392082, "children": { "RLTrainer._checkpoint": { "total": 0.17890759600004458, "count": 1, "self": 0.17890759600004458 } } } } } } }