{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4041937589645386, "min": 1.4041937589645386, "max": 1.4274570941925049, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71595.625, "min": 68286.28125, "max": 78755.1171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.83302411873841, "min": 75.23628048780488, "max": 372.45522388059703, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49498.0, "min": 48804.0, "max": 50235.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999933.0, "min": 49642.0, "max": 1999933.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999933.0, "min": 49642.0, "max": 1999933.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4859137535095215, "min": 0.07197359204292297, "max": 2.5241127014160156, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1339.907470703125, "min": 9.572487831115723, "max": 1633.185302734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7297718037258494, "min": 1.8903213681134963, "max": 4.011178852855295, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2010.3470022082329, "min": 251.412741959095, "max": 2597.3473808169365, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7297718037258494, "min": 1.8903213681134963, "max": 4.011178852855295, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2010.3470022082329, "min": 251.412741959095, "max": 2597.3473808169365, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01632381909827624, "min": 0.012627633497080144, "max": 0.020162087546648562, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04897145729482873, "min": 0.025255266994160287, "max": 0.060486262639945686, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04538160694970025, "min": 0.022504001886894304, "max": 0.06048426224539677, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13614482084910073, "min": 0.04500800377378861, "max": 0.17477726911505062, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7883987372333334e-06, "min": 3.7883987372333334e-06, "max": 0.00029535292654902503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.13651962117e-05, "min": 1.13651962117e-05, "max": 0.0008442325685891498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126276666666671, "min": 0.10126276666666671, "max": 0.19845097500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037883000000001, "min": 0.20767204999999997, "max": 0.5814108500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.301205666666666e-05, "min": 7.301205666666666e-05, "max": 0.004922703652499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021903617, "min": 0.00021903617, "max": 0.014072401415, "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": "1713881496", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713883901" }, "total": 2404.778123204, "count": 1, "self": 0.4432253600002696, "children": { "run_training.setup": { "total": 0.05288114699999369, "count": 1, "self": 0.05288114699999369 }, "TrainerController.start_learning": { "total": 2404.282016697, "count": 1, "self": 4.211144920044262, "children": { "TrainerController._reset_env": { "total": 2.994836550000059, "count": 1, "self": 2.994836550000059 }, "TrainerController.advance": { "total": 2396.965094364956, "count": 233089, "self": 4.594852528172396, "children": { "env_step": { "total": 1904.0430853527714, "count": 233089, "self": 1583.9599391238696, "children": { "SubprocessEnvManager._take_step": { "total": 317.2967633229281, "count": 233089, "self": 16.846434021827804, "children": { "TorchPolicy.evaluate": { "total": 300.4503293011003, "count": 223086, "self": 300.4503293011003 } } }, "workers": { "total": 2.78638290597371, "count": 233089, "self": 0.0, "children": { "worker_root": { "total": 2397.2100328150036, "count": 233089, "is_parallel": true, "self": 1113.0032388040856, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009307579999813242, "count": 1, "is_parallel": true, "self": 0.00023462099989046692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006961370000908573, "count": 2, "is_parallel": true, "self": 0.0006961370000908573 } } }, "UnityEnvironment.step": { "total": 0.030925238000008903, "count": 1, "is_parallel": true, "self": 0.0004123600000411898, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023621700006515312, "count": 1, "is_parallel": true, "self": 0.00023621700006515312 }, "communicator.exchange": { "total": 0.02947412899993651, "count": 1, "is_parallel": true, "self": 0.02947412899993651 }, "steps_from_proto": { "total": 0.0008025319999660496, "count": 1, "is_parallel": true, "self": 0.00021116699986123422, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005913650001048154, "count": 2, "is_parallel": true, "self": 0.0005913650001048154 } } } } } } }, "UnityEnvironment.step": { "total": 1284.206794010918, "count": 233088, "is_parallel": true, "self": 39.76371589204223, "children": { "UnityEnvironment._generate_step_input": { "total": 82.06901361692132, "count": 233088, "is_parallel": true, "self": 82.06901361692132 }, "communicator.exchange": { "total": 1070.773338251051, "count": 233088, "is_parallel": true, "self": 1070.773338251051 }, "steps_from_proto": { "total": 91.60072625090334, "count": 233088, "is_parallel": true, "self": 32.72742000391315, "children": { "_process_rank_one_or_two_observation": { "total": 58.87330624699018, "count": 466176, "is_parallel": true, "self": 58.87330624699018 } } } } } } } } } } }, "trainer_advance": { "total": 488.327156484012, "count": 233089, "self": 6.480847687012442, "children": { "process_trajectory": { "total": 154.01561451499845, "count": 233089, "self": 152.66543603899777, "children": { "RLTrainer._checkpoint": { "total": 1.3501784760006785, "count": 10, "self": 1.3501784760006785 } } }, "_update_policy": { "total": 327.8306942820011, "count": 97, "self": 265.4922272300032, "children": { "TorchPPOOptimizer.update": { "total": 62.338467051997895, "count": 2910, "self": 62.338467051997895 } } } } } } }, "trainer_threads": { "total": 8.199999683711212e-07, "count": 1, "self": 8.199999683711212e-07 }, "TrainerController._save_models": { "total": 0.11094004200003837, "count": 1, "self": 0.0019729840000763943, "children": { "RLTrainer._checkpoint": { "total": 0.10896705799996198, "count": 1, "self": 0.10896705799996198 } } } } } } }