{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4025816917419434, "min": 1.4025816917419434, "max": 1.43050217628479, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71353.5390625, "min": 69140.921875, "max": 75337.28125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.01470588235294, "min": 77.77637795275591, "max": 391.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49512.0, "min": 48735.0, "max": 50092.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49855.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49855.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4658141136169434, "min": 0.06485355645418167, "max": 2.5078182220458984, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1341.40283203125, "min": 8.236401557922363, "max": 1522.7921142578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8416563672397066, "min": 1.6902434131291908, "max": 4.021965499456764, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2089.8610637784004, "min": 214.66091346740723, "max": 2473.5079205036163, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8416563672397066, "min": 1.6902434131291908, "max": 4.021965499456764, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2089.8610637784004, "min": 214.66091346740723, "max": 2473.5079205036163, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01568843168024614, "min": 0.013536816570558585, "max": 0.019978830625768752, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04706529504073842, "min": 0.02707363314111717, "max": 0.05458764061331749, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05021466550727685, "min": 0.023670885546339882, "max": 0.06368641642232736, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15064399652183055, "min": 0.04833814638356368, "max": 0.17353701790173848, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.579748806783334e-06, "min": 3.579748806783334e-06, "max": 0.000295368526543825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0739246420350001e-05, "min": 1.0739246420350001e-05, "max": 0.0008439709686763498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119321666666665, "min": 0.10119321666666665, "max": 0.198456175, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30357965, "min": 0.20757750000000003, "max": 0.58132365, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.954151166666668e-05, "min": 6.954151166666668e-05, "max": 0.0049229631324999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020862453500000003, "min": 0.00020862453500000003, "max": 0.014068050135000003, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679078309", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1679081152" }, "total": 2842.90650145, "count": 1, "self": 0.48667898799976683, "children": { "run_training.setup": { "total": 0.20238864500004183, "count": 1, "self": 0.20238864500004183 }, "TrainerController.start_learning": { "total": 2842.2174338170003, "count": 1, "self": 6.042242260892635, "children": { "TrainerController._reset_env": { "total": 8.799342565000018, "count": 1, "self": 8.799342565000018 }, "TrainerController.advance": { "total": 2827.2360904631078, "count": 233006, "self": 6.71282763605268, "children": { "env_step": { "total": 2225.6055971720857, "count": 233006, "self": 1869.7266466861836, "children": { "SubprocessEnvManager._take_step": { "total": 352.05855485595964, "count": 233006, "self": 22.012712248911953, "children": { "TorchPolicy.evaluate": { "total": 330.0458426070477, "count": 223098, "self": 330.0458426070477 } } }, "workers": { "total": 3.820395629942425, "count": 233006, "self": 0.0, "children": { "worker_root": { "total": 2831.5196850159996, "count": 233006, "is_parallel": true, "self": 1326.870986637004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012588779999873623, "count": 1, "is_parallel": true, "self": 0.0003863189999151473, "children": { "_process_rank_one_or_two_observation": { "total": 0.000872559000072215, "count": 2, "is_parallel": true, "self": 0.000872559000072215 } } }, "UnityEnvironment.step": { "total": 0.0331904189999932, "count": 1, "is_parallel": true, "self": 0.00034767600004670385, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023169700000380544, "count": 1, "is_parallel": true, "self": 0.00023169700000380544 }, "communicator.exchange": { "total": 0.03184348899998213, "count": 1, "is_parallel": true, "self": 0.03184348899998213 }, "steps_from_proto": { "total": 0.0007675569999605614, "count": 1, "is_parallel": true, "self": 0.00026046899995435524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005070880000062061, "count": 2, "is_parallel": true, "self": 0.0005070880000062061 } } } } } } }, "UnityEnvironment.step": { "total": 1504.6486983789955, "count": 233005, "is_parallel": true, "self": 44.71176322409906, "children": { "UnityEnvironment._generate_step_input": { "total": 91.26975914195214, "count": 233005, "is_parallel": true, "self": 91.26975914195214 }, "communicator.exchange": { "total": 1262.6458345830324, "count": 233005, "is_parallel": true, "self": 1262.6458345830324 }, "steps_from_proto": { "total": 106.02134142991184, "count": 233005, "is_parallel": true, "self": 41.23617389093374, "children": { "_process_rank_one_or_two_observation": { "total": 64.7851675389781, "count": 466010, "is_parallel": true, "self": 64.7851675389781 } } } } } } } } } } }, "trainer_advance": { "total": 594.9176656549694, "count": 233006, "self": 9.314105746011364, "children": { "process_trajectory": { "total": 167.6560645339573, "count": 233006, "self": 166.3322801999576, "children": { "RLTrainer._checkpoint": { "total": 1.323784333999697, "count": 10, "self": 1.323784333999697 } } }, "_update_policy": { "total": 417.9474953750007, "count": 97, "self": 353.8936465609996, "children": { "TorchPPOOptimizer.update": { "total": 64.05384881400107, "count": 2910, "self": 64.05384881400107 } } } } } } }, "trainer_threads": { "total": 1.6250000953732524e-06, "count": 1, "self": 1.6250000953732524e-06 }, "TrainerController._save_models": { "total": 0.13975690299957932, "count": 1, "self": 0.002255124999464897, "children": { "RLTrainer._checkpoint": { "total": 0.13750177800011443, "count": 1, "self": 0.13750177800011443 } } } } } } }