{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408327341079712, "min": 1.408327341079712, "max": 1.4273402690887451, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71154.328125, "min": 69254.875, "max": 76942.4609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.13178294573643, "min": 83.48801369863014, "max": 381.39694656488547, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50120.0, "min": 48757.0, "max": 50148.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999903.0, "min": 49819.0, "max": 1999903.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999903.0, "min": 49819.0, "max": 1999903.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3655617237091064, "min": 0.06930004805326462, "max": 2.4402003288269043, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1220.6298828125, "min": 9.00900650024414, "max": 1405.2899169921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6467160029235735, "min": 1.5885832346975803, "max": 3.9155124207633136, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1881.705457508564, "min": 206.51582051068544, "max": 2216.10943120718, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6467160029235735, "min": 1.5885832346975803, "max": 3.9155124207633136, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1881.705457508564, "min": 206.51582051068544, "max": 2216.10943120718, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.021759106181303247, "min": 0.014303531300780985, "max": 0.021759106181303247, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.06527731854390974, "min": 0.02888489263447506, "max": 0.06527731854390974, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04874928332865238, "min": 0.02250079748531183, "max": 0.060094226855370726, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14624784998595713, "min": 0.04500159497062366, "max": 0.18028268056611219, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.569798810099997e-06, "min": 3.569798810099997e-06, "max": 0.00029536395154535, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0709396430299991e-05, "min": 1.0709396430299991e-05, "max": 0.0008441088186303999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118990000000001, "min": 0.10118990000000001, "max": 0.19845465, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30356970000000005, "min": 0.20756240000000004, "max": 0.5813696, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.937600999999998e-05, "min": 6.937600999999998e-05, "max": 0.004922887035, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020812802999999996, "min": 0.00020812802999999996, "max": 0.014070343040000002, "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": "1671859160", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671861527" }, "total": 2367.487228419, "count": 1, "self": 0.4431527929996264, "children": { "run_training.setup": { "total": 0.11522986600016338, "count": 1, "self": 0.11522986600016338 }, "TrainerController.start_learning": { "total": 2366.92884576, "count": 1, "self": 4.12007627306366, "children": { "TrainerController._reset_env": { "total": 8.061984804000076, "count": 1, "self": 8.061984804000076 }, "TrainerController.advance": { "total": 2354.628329741937, "count": 231925, "self": 4.303294803885819, "children": { "env_step": { "total": 1853.983088012982, "count": 231925, "self": 1562.979692139977, "children": { "SubprocessEnvManager._take_step": { "total": 288.3243955831563, "count": 231925, "self": 14.883805764176486, "children": { "TorchPolicy.evaluate": { "total": 273.4405898189798, "count": 222988, "self": 68.17644977308328, "children": { "TorchPolicy.sample_actions": { "total": 205.2641400458965, "count": 222988, "self": 205.2641400458965 } } } } }, "workers": { "total": 2.679000289848773, "count": 231925, "self": 0.0, "children": { "worker_root": { "total": 2358.9124475899616, "count": 231925, "is_parallel": true, "self": 1066.0531339700044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023334969998813904, "count": 1, "is_parallel": true, "self": 0.00031515499995293794, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020183419999284524, "count": 2, "is_parallel": true, "self": 0.0020183419999284524 } } }, "UnityEnvironment.step": { "total": 0.029470119000052364, "count": 1, "is_parallel": true, "self": 0.00029025000003457535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001980649999495654, "count": 1, "is_parallel": true, "self": 0.0001980649999495654 }, "communicator.exchange": { "total": 0.02824405499995919, "count": 1, "is_parallel": true, "self": 0.02824405499995919 }, "steps_from_proto": { "total": 0.0007377490001090337, "count": 1, "is_parallel": true, "self": 0.00024688000007699884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004908690000320348, "count": 2, "is_parallel": true, "self": 0.0004908690000320348 } } } } } } }, "UnityEnvironment.step": { "total": 1292.8593136199572, "count": 231924, "is_parallel": true, "self": 36.783346785101, "children": { "UnityEnvironment._generate_step_input": { "total": 81.50723340877971, "count": 231924, "is_parallel": true, "self": 81.50723340877971 }, "communicator.exchange": { "total": 1076.4889785849175, "count": 231924, "is_parallel": true, "self": 1076.4889785849175 }, "steps_from_proto": { "total": 98.079754841159, "count": 231924, "is_parallel": true, "self": 40.10983460321245, "children": { "_process_rank_one_or_two_observation": { "total": 57.96992023794655, "count": 463848, "is_parallel": true, "self": 57.96992023794655 } } } } } } } } } } }, "trainer_advance": { "total": 496.3419469250689, "count": 231925, "self": 6.354400257992438, "children": { "process_trajectory": { "total": 154.46617570007515, "count": 231925, "self": 153.0976543560755, "children": { "RLTrainer._checkpoint": { "total": 1.368521343999646, "count": 10, "self": 1.368521343999646 } } }, "_update_policy": { "total": 335.5213709670013, "count": 97, "self": 281.8443740310224, "children": { "TorchPPOOptimizer.update": { "total": 53.67699693597888, "count": 2910, "self": 53.67699693597888 } } } } } } }, "trainer_threads": { "total": 8.989995876618195e-07, "count": 1, "self": 8.989995876618195e-07 }, "TrainerController._save_models": { "total": 0.11845404199993936, "count": 1, "self": 0.0020404599999892525, "children": { "RLTrainer._checkpoint": { "total": 0.11641358199995011, "count": 1, "self": 0.11641358199995011 } } } } } } }