{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4124107360839844, "min": 1.4124107360839844, "max": 1.4290417432785034, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70304.15625, "min": 67367.9296875, "max": 76930.7265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 113.91724137931034, "min": 100.47154471544715, "max": 414.64462809917353, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49554.0, "min": 48929.0, "max": 50172.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49896.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49896.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.351592540740967, "min": 0.08524911850690842, "max": 2.398319721221924, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1022.9427490234375, "min": 10.229894638061523, "max": 1166.95751953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6346657198050925, "min": 1.962866976733009, "max": 3.914022341673315, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1581.0795881152153, "min": 235.54403720796108, "max": 1855.4847029447556, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6346657198050925, "min": 1.962866976733009, "max": 3.914022341673315, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1581.0795881152153, "min": 235.54403720796108, "max": 1855.4847029447556, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015509579921167138, "min": 0.013749823909084725, "max": 0.019844088738227586, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.046528739763501414, "min": 0.028126341480674454, "max": 0.053676356943651624, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04788894421524472, "min": 0.022138146155824264, "max": 0.05214091166853905, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14366683264573415, "min": 0.04427629231164853, "max": 0.15248499934871992, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.334948888383345e-06, "min": 3.334948888383345e-06, "max": 0.0002953534515488499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0004846665150035e-05, "min": 1.0004846665150035e-05, "max": 0.0008441199186267, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111161666666668, "min": 0.10111161666666668, "max": 0.19845115, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30333485000000004, "min": 0.20736555, "max": 0.5813733, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.546967166666687e-05, "min": 6.546967166666687e-05, "max": 0.004922712385, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001964090150000006, "min": 0.0001964090150000006, "max": 0.01407052767, "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": "1735326119", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735328685" }, "total": 2566.281173313, "count": 1, "self": 0.429152716000317, "children": { "run_training.setup": { "total": 0.06002746199999365, "count": 1, "self": 0.06002746199999365 }, "TrainerController.start_learning": { "total": 2565.7919931349998, "count": 1, "self": 4.764650507994247, "children": { "TrainerController._reset_env": { "total": 4.97461395199997, "count": 1, "self": 4.97461395199997 }, "TrainerController.advance": { "total": 2555.9344174360053, "count": 231208, "self": 4.906926214054238, "children": { "env_step": { "total": 2018.3268797690012, "count": 231208, "self": 1587.1177196410015, "children": { "SubprocessEnvManager._take_step": { "total": 428.20409743909164, "count": 231208, "self": 16.253349633062726, "children": { "TorchPolicy.evaluate": { "total": 411.9507478060289, "count": 222976, "self": 411.9507478060289 } } }, "workers": { "total": 3.005062688908083, "count": 231208, "self": 0.0, "children": { "worker_root": { "total": 2558.1503786840112, "count": 231208, "is_parallel": true, "self": 1269.2153336230263, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007869269999787321, "count": 1, "is_parallel": true, "self": 0.00021181800002523232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005751089999534997, "count": 2, "is_parallel": true, "self": 0.0005751089999534997 } } }, "UnityEnvironment.step": { "total": 0.03740131699998983, "count": 1, "is_parallel": true, "self": 0.00040219899995008745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020915900000773036, "count": 1, "is_parallel": true, "self": 0.00020915900000773036 }, "communicator.exchange": { "total": 0.036003671000003123, "count": 1, "is_parallel": true, "self": 0.036003671000003123 }, "steps_from_proto": { "total": 0.0007862880000288897, "count": 1, "is_parallel": true, "self": 0.00021476099999517828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005715270000337114, "count": 2, "is_parallel": true, "self": 0.0005715270000337114 } } } } } } }, "UnityEnvironment.step": { "total": 1288.935045060985, "count": 231207, "is_parallel": true, "self": 38.12779320897653, "children": { "UnityEnvironment._generate_step_input": { "total": 84.00828435997664, "count": 231207, "is_parallel": true, "self": 84.00828435997664 }, "communicator.exchange": { "total": 1074.2985213089064, "count": 231207, "is_parallel": true, "self": 1074.2985213089064 }, "steps_from_proto": { "total": 92.50044618312546, "count": 231207, "is_parallel": true, "self": 34.0553349592152, "children": { "_process_rank_one_or_two_observation": { "total": 58.44511122391026, "count": 462414, "is_parallel": true, "self": 58.44511122391026 } } } } } } } } } } }, "trainer_advance": { "total": 532.7006114529499, "count": 231208, "self": 7.219701127814005, "children": { "process_trajectory": { "total": 166.36881573813554, "count": 231208, "self": 164.92700739613605, "children": { "RLTrainer._checkpoint": { "total": 1.44180834199949, "count": 10, "self": 1.44180834199949 } } }, "_update_policy": { "total": 359.11209458700046, "count": 97, "self": 288.7567030539977, "children": { "TorchPPOOptimizer.update": { "total": 70.35539153300277, "count": 2910, "self": 70.35539153300277 } } } } } } }, "trainer_threads": { "total": 1.3490002856997307e-06, "count": 1, "self": 1.3490002856997307e-06 }, "TrainerController._save_models": { "total": 0.1183098900000914, "count": 1, "self": 0.0028189800004838617, "children": { "RLTrainer._checkpoint": { "total": 0.11549090999960754, "count": 1, "self": 0.11549090999960754 } } } } } } }