{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9198381900787354, "min": 0.8994337916374207, "max": 2.8842244148254395, "count": 48 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4735.3271484375, "min": 4104.0546875, "max": 15133.525390625, "count": 48 }, "SnowballTarget.Step.mean": { "value": 239992.0, "min": 4976.0, "max": 239992.0, "count": 48 }, "SnowballTarget.Step.sum": { "value": 239992.0, "min": 4976.0, "max": 239992.0, "count": 48 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.657969951629639, "min": 0.14411304891109467, "max": 6.657969951629639, "count": 48 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 712.4027709960938, "min": 13.978965759277344, "max": 712.4027709960938, "count": 48 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 48 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 6567.0, "min": 4378.0, "max": 6567.0, "count": 48 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.056694410855556966, "min": 0.056694410855556966, "max": 0.08209888453369357, "count": 48 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1700832325666709, "min": 0.128328250721097, "max": 0.2210522196027359, "count": 48 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1775992400213784, "min": 0.06960111978125996, "max": 0.2161282835637822, "count": 48 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5327977200641352, "min": 0.13920223956251992, "max": 0.6474899941799688, "count": 48 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.110098963333324e-06, "min": 3.110098963333324e-06, "max": 0.0002959850013383333, "count": 48 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.330296889999971e-06, "min": 9.330296889999971e-06, "max": 0.0008343300218899999, "count": 48 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103666666666668, "min": 0.10103666666666668, "max": 0.19866166666666668, "count": 48 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.30311000000000005, "min": 0.20665666666666666, "max": 0.57811, "count": 48 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.172966666666651e-05, "min": 6.172966666666651e-05, "max": 0.004933217166666667, "count": 48 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00018518899999999953, "min": 0.00018518899999999953, "max": 0.013907689, "count": 48 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.0, "min": 2.8181818181818183, "max": 26.5, "count": 48 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 858.0, "min": 62.0, "max": 858.0, "count": 48 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.0, "min": 2.8181818181818183, "max": 26.5, "count": 48 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 858.0, "min": 62.0, "max": 858.0, "count": 48 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694188906", "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", "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": "1694189518" }, "total": 611.9584227450001, "count": 1, "self": 0.4347668630002772, "children": { "run_training.setup": { "total": 0.07874301399999695, "count": 1, "self": 0.07874301399999695 }, "TrainerController.start_learning": { "total": 611.4449128679998, "count": 1, "self": 0.7245851959883112, "children": { "TrainerController._reset_env": { "total": 4.714997414000095, "count": 1, "self": 4.714997414000095 }, "TrainerController.advance": { "total": 605.8523994740116, "count": 21873, "self": 0.37076138601935327, "children": { "env_step": { "total": 605.4816380879922, "count": 21873, "self": 438.8264531169949, "children": { "SubprocessEnvManager._take_step": { "total": 166.28702373598253, "count": 21873, "self": 2.351438181967751, "children": { "TorchPolicy.evaluate": { "total": 163.93558555401478, "count": 21873, "self": 163.93558555401478 } } }, "workers": { "total": 0.3681612350147816, "count": 21873, "self": 0.0, "children": { "worker_root": { "total": 609.4026303500146, "count": 21873, "is_parallel": true, "self": 286.166460385013, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008090703999982907, "count": 1, "is_parallel": true, "self": 0.005341050999959407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027496530000234998, "count": 10, "is_parallel": true, "self": 0.0027496530000234998 } } }, "UnityEnvironment.step": { "total": 0.042507893999982116, "count": 1, "is_parallel": true, "self": 0.0007802269999501732, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039228599996476987, "count": 1, "is_parallel": true, "self": 0.00039228599996476987 }, "communicator.exchange": { "total": 0.038755118000040056, "count": 1, "is_parallel": true, "self": 0.038755118000040056 }, "steps_from_proto": { "total": 0.0025802630000271165, "count": 1, "is_parallel": true, "self": 0.00047196900027302036, "children": { "_process_rank_one_or_two_observation": { "total": 0.002108293999754096, "count": 10, "is_parallel": true, "self": 0.002108293999754096 } } } } } } }, "UnityEnvironment.step": { "total": 323.23616996500164, "count": 21872, "is_parallel": true, "self": 13.559752229012474, "children": { "UnityEnvironment._generate_step_input": { "total": 7.082381256014173, "count": 21872, "is_parallel": true, "self": 7.082381256014173 }, "communicator.exchange": { "total": 254.37697278798362, "count": 21872, "is_parallel": true, "self": 254.37697278798362 }, "steps_from_proto": { "total": 48.21706369199137, "count": 21872, "is_parallel": true, "self": 8.775731177993634, "children": { "_process_rank_one_or_two_observation": { "total": 39.441332513997736, "count": 218720, "is_parallel": true, "self": 39.441332513997736 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023845600003369327, "count": 1, "self": 0.00023845600003369327, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 601.0758448789713, "count": 548295, "is_parallel": true, "self": 13.320307015923618, "children": { "process_trajectory": { "total": 329.85051734504793, "count": 548295, "is_parallel": true, "self": 328.29295691704783, "children": { "RLTrainer._checkpoint": { "total": 1.5575604280001016, "count": 6, "is_parallel": true, "self": 1.5575604280001016 } } }, "_update_policy": { "total": 257.9050205179998, "count": 109, "is_parallel": true, "self": 99.70730488800257, "children": { "TorchPPOOptimizer.update": { "total": 158.19771562999722, "count": 5553, "is_parallel": true, "self": 158.19771562999722 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15269232799983, "count": 1, "self": 0.0009346859999368462, "children": { "RLTrainer._checkpoint": { "total": 0.15175764199989317, "count": 1, "self": 0.15175764199989317 } } } } } } }