{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4085352420806885, "min": 1.4085352420806885, "max": 1.4290231466293335, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70073.21875, "min": 69196.1484375, "max": 78923.796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.96661101836393, "min": 73.62593144560358, "max": 405.8467741935484, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49098.0, "min": 48677.0, "max": 50325.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999995.0, "min": 49933.0, "max": 1999995.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999995.0, "min": 49933.0, "max": 1999995.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4735732078552246, "min": -0.00145780760794878, "max": 2.5335779190063477, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1481.67041015625, "min": -0.17931033670902252, "max": 1649.682861328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8244214248975648, "min": 1.7816440990058386, "max": 4.029986271537653, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2290.8284335136414, "min": 219.14222417771816, "max": 2599.459308743477, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8244214248975648, "min": 1.7816440990058386, "max": 4.029986271537653, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2290.8284335136414, "min": 219.14222417771816, "max": 2599.459308743477, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016293251192999177, "min": 0.0131359313808692, "max": 0.02031431114616377, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04887975357899753, "min": 0.0262718627617384, "max": 0.056178481210372416, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056266425053278606, "min": 0.023091238364577292, "max": 0.06658290103077888, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1687992751598358, "min": 0.046182476729154584, "max": 0.1870453217377265, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.698698767133342e-06, "min": 3.698698767133342e-06, "max": 0.00029536132654622496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1096096301400026e-05, "min": 1.1096096301400026e-05, "max": 0.0008440617186461, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123286666666668, "min": 0.10123286666666668, "max": 0.198453775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30369860000000004, "min": 0.20761075000000007, "max": 0.5813539000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.15200466666668e-05, "min": 7.15200466666668e-05, "max": 0.004922843372499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021456014000000037, "min": 0.00021456014000000037, "max": 0.014069559610000004, "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": "1713083079", "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": "1713087071" }, "total": 3991.688719231, "count": 1, "self": 0.6001302790000409, "children": { "run_training.setup": { "total": 0.06742270699999153, "count": 1, "self": 0.06742270699999153 }, "TrainerController.start_learning": { "total": 3991.021166245, "count": 1, "self": 7.434541048944993, "children": { "TrainerController._reset_env": { "total": 3.0186280209999836, "count": 1, "self": 3.0186280209999836 }, "TrainerController.advance": { "total": 3980.4338085880545, "count": 232963, "self": 7.67678817599608, "children": { "env_step": { "total": 2558.4984012711184, "count": 232963, "self": 2144.852699855165, "children": { "SubprocessEnvManager._take_step": { "total": 408.97067985598545, "count": 232963, "self": 24.74999744692758, "children": { "TorchPolicy.evaluate": { "total": 384.2206824090579, "count": 222956, "self": 384.2206824090579 } } }, "workers": { "total": 4.675021559967604, "count": 232963, "self": 0.0, "children": { "worker_root": { "total": 3978.7438563279434, "count": 232963, "is_parallel": true, "self": 2279.5129294889393, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009346389999791427, "count": 1, "is_parallel": true, "self": 0.00023665099996605932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006979880000130834, "count": 2, "is_parallel": true, "self": 0.0006979880000130834 } } }, "UnityEnvironment.step": { "total": 0.03491451799999368, "count": 1, "is_parallel": true, "self": 0.00042818599996508055, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018963799999482944, "count": 1, "is_parallel": true, "self": 0.00018963799999482944 }, "communicator.exchange": { "total": 0.03341604500002404, "count": 1, "is_parallel": true, "self": 0.03341604500002404 }, "steps_from_proto": { "total": 0.0008806490000097256, "count": 1, "is_parallel": true, "self": 0.00024015000002464149, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006404989999850841, "count": 2, "is_parallel": true, "self": 0.0006404989999850841 } } } } } } }, "UnityEnvironment.step": { "total": 1699.230926839004, "count": 232962, "is_parallel": true, "self": 53.76458163271354, "children": { "UnityEnvironment._generate_step_input": { "total": 85.10463454502633, "count": 232962, "is_parallel": true, "self": 85.10463454502633 }, "communicator.exchange": { "total": 1434.0736740111493, "count": 232962, "is_parallel": true, "self": 1434.0736740111493 }, "steps_from_proto": { "total": 126.28803665011492, "count": 232962, "is_parallel": true, "self": 41.96023187105476, "children": { "_process_rank_one_or_two_observation": { "total": 84.32780477906016, "count": 465924, "is_parallel": true, "self": 84.32780477906016 } } } } } } } } } } }, "trainer_advance": { "total": 1414.25861914094, "count": 232963, "self": 11.16802621687043, "children": { "process_trajectory": { "total": 223.95317462706674, "count": 232963, "self": 222.72915540806565, "children": { "RLTrainer._checkpoint": { "total": 1.224019219001093, "count": 10, "self": 1.224019219001093 } } }, "_update_policy": { "total": 1179.1374182970028, "count": 97, "self": 325.93947110600357, "children": { "TorchPPOOptimizer.update": { "total": 853.1979471909992, "count": 2910, "self": 853.1979471909992 } } } } } } }, "trainer_threads": { "total": 1.052000698109623e-06, "count": 1, "self": 1.052000698109623e-06 }, "TrainerController._save_models": { "total": 0.13418753499990999, "count": 1, "self": 0.0029704369999308256, "children": { "RLTrainer._checkpoint": { "total": 0.13121709799997916, "count": 1, "self": 0.13121709799997916 } } } } } } }