{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4024590253829956, "min": 1.4024590253829956, "max": 1.425426721572876, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70733.0234375, "min": 69172.1875, "max": 77997.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.04187604690117, "min": 73.21333333333334, "max": 408.609756097561, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48979.0, "min": 48979.0, "max": 50259.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999946.0, "min": 49738.0, "max": 1999946.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999946.0, "min": 49738.0, "max": 1999946.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.449122428894043, "min": 0.022761015221476555, "max": 2.490082025527954, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1462.1260986328125, "min": 2.776843786239624, "max": 1621.0712890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8179091862098655, "min": 1.8257014546238008, "max": 3.977142985578607, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2279.2917841672897, "min": 222.7355774641037, "max": 2533.6747826337814, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8179091862098655, "min": 1.8257014546238008, "max": 3.977142985578607, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2279.2917841672897, "min": 222.7355774641037, "max": 2533.6747826337814, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015054719302214734, "min": 0.01327101015485823, "max": 0.019777880599334212, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0451641579066442, "min": 0.02654202030971646, "max": 0.05826030284612595, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05834816147883733, "min": 0.022221333533525466, "max": 0.06189918749862247, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.175044484436512, "min": 0.04444266706705093, "max": 0.1856975624958674, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.827948724050001e-06, "min": 3.827948724050001e-06, "max": 0.00029535270154909993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1483846172150003e-05, "min": 1.1483846172150003e-05, "max": 0.0008442480185839999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127594999999999, "min": 0.10127594999999999, "max": 0.19845090000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30382784999999995, "min": 0.2076848, "max": 0.581416, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.3669905e-05, "min": 7.3669905e-05, "max": 0.004922699910000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000221009715, "min": 0.000221009715, "max": 0.0140726584, "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": "1713181284", "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": "1713184835" }, "total": 3551.4415395000015, "count": 1, "self": 0.7936592000023666, "children": { "run_training.setup": { "total": 0.06949519999943732, "count": 1, "self": 0.06949519999943732 }, "TrainerController.start_learning": { "total": 3550.5783850999997, "count": 1, "self": 6.975091200036331, "children": { "TrainerController._reset_env": { "total": 22.588077300000805, "count": 1, "self": 22.588077300000805 }, "TrainerController.advance": { "total": 3520.7795422999643, "count": 232833, "self": 7.049110999818367, "children": { "env_step": { "total": 2884.5523190997937, "count": 232833, "self": 2071.721074399835, "children": { "SubprocessEnvManager._take_step": { "total": 808.1586945002055, "count": 232833, "self": 23.263080200893455, "children": { "TorchPolicy.evaluate": { "total": 784.895614299312, "count": 222934, "self": 784.895614299312 } } }, "workers": { "total": 4.672550199753459, "count": 232833, "self": 0.0, "children": { "worker_root": { "total": 3536.8728992997585, "count": 232833, "is_parallel": true, "self": 1847.6314621996717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001351700000668643, "count": 1, "is_parallel": true, "self": 0.0004884000009042211, "children": { "_process_rank_one_or_two_observation": { "total": 0.000863299999764422, "count": 2, "is_parallel": true, "self": 0.000863299999764422 } } }, "UnityEnvironment.step": { "total": 0.03617630000007921, "count": 1, "is_parallel": true, "self": 0.0003071999999519903, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004129999997530831, "count": 1, "is_parallel": true, "self": 0.0004129999997530831 }, "communicator.exchange": { "total": 0.03412390000084997, "count": 1, "is_parallel": true, "self": 0.03412390000084997 }, "steps_from_proto": { "total": 0.001332199999524164, "count": 1, "is_parallel": true, "self": 0.0001967999996850267, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011353999998391373, "count": 2, "is_parallel": true, "self": 0.0011353999998391373 } } } } } } }, "UnityEnvironment.step": { "total": 1689.2414371000868, "count": 232832, "is_parallel": true, "self": 38.271573399986664, "children": { "UnityEnvironment._generate_step_input": { "total": 60.845525599463144, "count": 232832, "is_parallel": true, "self": 60.845525599463144 }, "communicator.exchange": { "total": 1509.4851108005168, "count": 232832, "is_parallel": true, "self": 1509.4851108005168 }, "steps_from_proto": { "total": 80.63922730012018, "count": 232832, "is_parallel": true, "self": 30.086673400908694, "children": { "_process_rank_one_or_two_observation": { "total": 50.55255389921149, "count": 465664, "is_parallel": true, "self": 50.55255389921149 } } } } } } } } } } }, "trainer_advance": { "total": 629.1781122003522, "count": 232833, "self": 9.679002599983505, "children": { "process_trajectory": { "total": 233.13631700036967, "count": 232833, "self": 230.7127011003704, "children": { "RLTrainer._checkpoint": { "total": 2.4236158999992767, "count": 10, "self": 2.4236158999992767 } } }, "_update_policy": { "total": 386.362792599999, "count": 97, "self": 292.42689839999184, "children": { "TorchPPOOptimizer.update": { "total": 93.93589420000717, "count": 2910, "self": 93.93589420000717 } } } } } } }, "trainer_threads": { "total": 2.2999993234407157e-06, "count": 1, "self": 2.2999993234407157e-06 }, "TrainerController._save_models": { "total": 0.23567199999888544, "count": 1, "self": 0.0030518999992636964, "children": { "RLTrainer._checkpoint": { "total": 0.23262009999962174, "count": 1, "self": 0.23262009999962174 } } } } } } }