{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8589422702789307, "min": 0.8580460548400879, "max": 2.864452600479126, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8257.87109375, "min": 8257.87109375, "max": 29334.859375, "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": 6.644832134246826, "min": 0.2912047207355499, "max": 6.68354606628418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1295.7423095703125, "min": 56.493717193603516, "max": 1370.126953125, "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": 0.06430497875493636, "min": 0.06430497875493636, "max": 0.07694870559611017, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25721991501974545, "min": 0.25721991501974545, "max": 0.36846489223428175, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15545412122874575, "min": 0.10290622460631901, "max": 0.23536927110570316, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.621816484914983, "min": 0.41162489842527605, "max": 1.1652824760359877, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382800001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10404100000000002, "min": 0.10404100000000002, "max": 0.245941, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4161640000000001, "min": 0.4161640000000001, "max": 1.19258, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.068181818181817, "min": 3.659090909090909, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 161.0, "max": 1440.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.659090909090909, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 161.0, "max": 1440.0, "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": "1677167870", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677168356" }, "total": 486.447042668, "count": 1, "self": 0.7089213289998497, "children": { "run_training.setup": { "total": 0.1948156990000598, "count": 1, "self": 0.1948156990000598 }, "TrainerController.start_learning": { "total": 485.5433056400001, "count": 1, "self": 0.5040288519912792, "children": { "TrainerController._reset_env": { "total": 9.295815273000017, "count": 1, "self": 9.295815273000017 }, "TrainerController.advance": { "total": 475.551472460009, "count": 18219, "self": 0.2722814090045631, "children": { "env_step": { "total": 475.27919105100443, "count": 18219, "self": 334.87283503802735, "children": { "SubprocessEnvManager._take_step": { "total": 140.14163396698518, "count": 18219, "self": 1.476088368975411, "children": { "TorchPolicy.evaluate": { "total": 138.66554559800977, "count": 18219, "self": 31.668689016014582, "children": { "TorchPolicy.sample_actions": { "total": 106.99685658199519, "count": 18219, "self": 106.99685658199519 } } } } }, "workers": { "total": 0.26472204599190263, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 484.10068521900337, "count": 18219, "is_parallel": true, "self": 251.33377600599738, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0045585370000935654, "count": 1, "is_parallel": true, "self": 0.0033063750000792425, "children": { "_process_rank_one_or_two_observation": { "total": 0.001252162000014323, "count": 10, "is_parallel": true, "self": 0.001252162000014323 } } }, "UnityEnvironment.step": { "total": 0.03575979200002166, "count": 1, "is_parallel": true, "self": 0.0006862760000103663, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003334279999762657, "count": 1, "is_parallel": true, "self": 0.0003334279999762657 }, "communicator.exchange": { "total": 0.03263124300008258, "count": 1, "is_parallel": true, "self": 0.03263124300008258 }, "steps_from_proto": { "total": 0.0021088449999524528, "count": 1, "is_parallel": true, "self": 0.0004797869997901216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016290580001623312, "count": 10, "is_parallel": true, "self": 0.0016290580001623312 } } } } } } }, "UnityEnvironment.step": { "total": 232.766909213006, "count": 18218, "is_parallel": true, "self": 9.56572086800486, "children": { "UnityEnvironment._generate_step_input": { "total": 5.259873816017375, "count": 18218, "is_parallel": true, "self": 5.259873816017375 }, "communicator.exchange": { "total": 186.790524965008, "count": 18218, "is_parallel": true, "self": 186.790524965008 }, "steps_from_proto": { "total": 31.150789563975763, "count": 18218, "is_parallel": true, "self": 6.710519204923457, "children": { "_process_rank_one_or_two_observation": { "total": 24.440270359052306, "count": 182180, "is_parallel": true, "self": 24.440270359052306 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.401499985666305e-05, "count": 1, "self": 8.401499985666305e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.17427519898445, "count": 394119, "is_parallel": true, "self": 10.074679503966536, "children": { "process_trajectory": { "total": 252.82002343901695, "count": 394119, "is_parallel": true, "self": 251.36208151301685, "children": { "RLTrainer._checkpoint": { "total": 1.4579419260001032, "count": 4, "is_parallel": true, "self": 1.4579419260001032 } } }, "_update_policy": { "total": 209.27957225600096, "count": 90, "is_parallel": true, "self": 77.21600036200778, "children": { "TorchPPOOptimizer.update": { "total": 132.06357189399318, "count": 6116, "is_parallel": true, "self": 132.06357189399318 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1919050399999378, "count": 1, "self": 0.0011855079999349982, "children": { "RLTrainer._checkpoint": { "total": 0.1907195320000028, "count": 1, "self": 0.1907195320000028 } } } } } } }