{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8154197931289673, "min": 0.7803208827972412, "max": 2.87243914604187, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7893.263671875, "min": 7696.3876953125, "max": 29511.439453125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.973355293273926, "min": 0.17810222506523132, "max": 13.973355293273926, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2864.537841796875, "min": 34.55183029174805, "max": 2864.537841796875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.10110816852110849, "min": 0.09207196997097829, "max": 0.10495116637737774, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.5055408426055424, "min": 0.36828787988391315, "max": 0.5247558318868887, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17249566183662884, "min": 0.10472808884975815, "max": 0.2765142716321291, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8624783091831442, "min": 0.4189123553990326, "max": 1.3825713581606456, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.0002967528010824, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.0014540640153119999, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1010176, "min": 0.1010176, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.505088, "min": 0.4119904000000001, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.077824000000005e-05, "min": 6.077824000000005e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030389120000000027, "min": 0.00030389120000000027, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.272727272727273, "min": 2.909090909090909, "max": 27.727272727272727, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1500.0, "min": 128.0, "max": 1525.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.272727272727273, "min": 2.909090909090909, "max": 27.727272727272727, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1500.0, "min": 128.0, "max": 1525.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693537561", "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 --force", "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": "1693538906" }, "total": 1345.6031435730001, "count": 1, "self": 0.4333431500001552, "children": { "run_training.setup": { "total": 0.037793475999933435, "count": 1, "self": 0.037793475999933435 }, "TrainerController.start_learning": { "total": 1345.132006947, "count": 1, "self": 1.4984556720194178, "children": { "TrainerController._reset_env": { "total": 4.896265611999979, "count": 1, "self": 4.896265611999979 }, "TrainerController.advance": { "total": 1338.5715142539805, "count": 45479, "self": 0.6964405999874543, "children": { "env_step": { "total": 1337.875073653993, "count": 45479, "self": 1028.0208163249995, "children": { "SubprocessEnvManager._take_step": { "total": 309.13317156601136, "count": 45479, "self": 4.533843033995026, "children": { "TorchPolicy.evaluate": { "total": 304.59932853201633, "count": 45479, "self": 304.59932853201633 } } }, "workers": { "total": 0.7210857629821703, "count": 45479, "self": 0.0, "children": { "worker_root": { "total": 1340.9624088599712, "count": 45479, "is_parallel": true, "self": 693.7972370709555, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001840314999981274, "count": 1, "is_parallel": true, "self": 0.0005099809998228011, "children": { "_process_rank_one_or_two_observation": { "total": 0.001330334000158473, "count": 10, "is_parallel": true, "self": 0.001330334000158473 } } }, "UnityEnvironment.step": { "total": 0.11518885500004217, "count": 1, "is_parallel": true, "self": 0.0006118479998349358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004302970000935602, "count": 1, "is_parallel": true, "self": 0.0004302970000935602 }, "communicator.exchange": { "total": 0.10830016500005968, "count": 1, "is_parallel": true, "self": 0.10830016500005968 }, "steps_from_proto": { "total": 0.005846545000053993, "count": 1, "is_parallel": true, "self": 0.0014629529998728685, "children": { "_process_rank_one_or_two_observation": { "total": 0.004383592000181125, "count": 10, "is_parallel": true, "self": 0.004383592000181125 } } } } } } }, "UnityEnvironment.step": { "total": 647.1651717890157, "count": 45478, "is_parallel": true, "self": 26.901153625059578, "children": { "UnityEnvironment._generate_step_input": { "total": 14.06952610297185, "count": 45478, "is_parallel": true, "self": 14.06952610297185 }, "communicator.exchange": { "total": 510.355672680986, "count": 45478, "is_parallel": true, "self": 510.355672680986 }, "steps_from_proto": { "total": 95.83881937999831, "count": 45478, "is_parallel": true, "self": 17.614221908010336, "children": { "_process_rank_one_or_two_observation": { "total": 78.22459747198798, "count": 454780, "is_parallel": true, "self": 78.22459747198798 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001644690000830451, "count": 1, "self": 0.0001644690000830451, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1329.2282989060436, "count": 1141419, "is_parallel": true, "self": 25.643506672062358, "children": { "process_trajectory": { "total": 665.1284824269806, "count": 1141419, "is_parallel": true, "self": 660.9623594279803, "children": { "RLTrainer._checkpoint": { "total": 4.166122999000208, "count": 10, "is_parallel": true, "self": 4.166122999000208 } } }, "_update_policy": { "total": 638.4563098070006, "count": 227, "is_parallel": true, "self": 185.51376595500676, "children": { "TorchPPOOptimizer.update": { "total": 452.94254385199383, "count": 23151, "is_parallel": true, "self": 452.94254385199383 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1656069400000888, "count": 1, "self": 0.0013124190004418779, "children": { "RLTrainer._checkpoint": { "total": 0.16429452099964692, "count": 1, "self": 0.16429452099964692 } } } } } } }