{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.871245861053467, "min": 2.871245861053467, "max": 2.871245861053467, "count": 1 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29467.595703125, "min": 29467.595703125, "max": 29467.595703125, "count": 1 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19350029528141022, "min": 0.19350029528141022, "max": 0.19350029528141022, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 37.539058685302734, "min": 37.539058685302734, "max": 37.539058685302734, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 8756.0, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06077112006061956, "min": 0.06077112006061956, "max": 0.06077112006061956, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24308448024247825, "min": 0.24308448024247825, "max": 0.24308448024247825, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12860633954223172, "min": 0.12860633954223172, "max": 0.12860633954223172, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5144253581689269, "min": 0.5144253581689269, "max": 0.5144253581689269, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00022940005411999998, "min": 0.00022940005411999998, "max": 0.00022940005411999998, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0009176002164799999, "min": 0.0009176002164799999, "max": 0.0009176002164799999, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.14588, "min": 0.14588, "max": 0.14588, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.58352, "min": 0.58352, "max": 0.58352, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.002299412, "min": 0.002299412, "max": 0.002299412, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.009197648, "min": 0.009197648, "max": 0.009197648, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 3.2045454545454546, "min": 3.2045454545454546, "max": 3.2045454545454546, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 141.0, "min": 141.0, "max": 141.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 3.2045454545454546, "min": 3.2045454545454546, "max": 3.2045454545454546, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 141.0, "min": 141.0, "max": 141.0, "count": 1 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690757484", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690757516" }, "total": 32.29701657800001, "count": 1, "self": 0.4326129780001793, "children": { "run_training.setup": { "total": 0.03678964599998835, "count": 1, "self": 0.03678964599998835 }, "TrainerController.start_learning": { "total": 31.827613953999844, "count": 1, "self": 0.052688158000137264, "children": { "TrainerController._reset_env": { "total": 5.295655569000019, "count": 1, "self": 5.295655569000019 }, "TrainerController.advance": { "total": 26.31787561400006, "count": 934, "self": 0.016715557000452463, "children": { "env_step": { "total": 26.301160056999606, "count": 934, "self": 19.308190097999386, "children": { "SubprocessEnvManager._take_step": { "total": 6.976216229000556, "count": 934, "self": 0.09144807400070931, "children": { "TorchPolicy.evaluate": { "total": 6.884768154999847, "count": 934, "self": 6.884768154999847 } } }, "workers": { "total": 0.016753729999663847, "count": 934, "self": 0.0, "children": { "worker_root": { "total": 31.585048957997287, "count": 934, "is_parallel": true, "self": 17.413109775998464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006592164999801753, "count": 1, "is_parallel": true, "self": 0.004779910999786807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018122540000149456, "count": 10, "is_parallel": true, "self": 0.0018122540000149456 } } }, "UnityEnvironment.step": { "total": 0.051494462000164276, "count": 1, "is_parallel": true, "self": 0.0005400480001753749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037356899997575965, "count": 1, "is_parallel": true, "self": 0.00037356899997575965 }, "communicator.exchange": { "total": 0.04809759399995528, "count": 1, "is_parallel": true, "self": 0.04809759399995528 }, "steps_from_proto": { "total": 0.0024832510000578623, "count": 1, "is_parallel": true, "self": 0.0004327730002842145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020504779997736478, "count": 10, "is_parallel": true, "self": 0.0020504779997736478 } } } } } } }, "UnityEnvironment.step": { "total": 14.171939181998823, "count": 933, "is_parallel": true, "self": 0.5773068859887189, "children": { "UnityEnvironment._generate_step_input": { "total": 0.3079306910046853, "count": 933, "is_parallel": true, "self": 0.3079306910046853 }, "communicator.exchange": { "total": 11.208800530999952, "count": 933, "is_parallel": true, "self": 11.208800530999952 }, "steps_from_proto": { "total": 2.0779010740054673, "count": 933, "is_parallel": true, "self": 0.3804511670175543, "children": { "_process_rank_one_or_two_observation": { "total": 1.697449906987913, "count": 9330, "is_parallel": true, "self": 1.697449906987913 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00024163799980669864, "count": 1, "self": 0.00024163799980669864, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 26.099451395997903, "count": 25800, "is_parallel": true, "self": 0.614665287010439, "children": { "process_trajectory": { "total": 15.276181148987234, "count": 25800, "is_parallel": true, "self": 15.276181148987234 }, "_update_policy": { "total": 10.20860496000023, "count": 4, "is_parallel": true, "self": 4.436457219998601, "children": { "TorchPPOOptimizer.update": { "total": 5.772147740001628, "count": 201, "is_parallel": true, "self": 5.772147740001628 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16115297499982262, "count": 1, "self": 0.0009271329997773137, "children": { "RLTrainer._checkpoint": { "total": 0.1602258420000453, "count": 1, "self": 0.1602258420000453 } } } } } } }