{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4020800590515137, "min": 1.4020756483078003, "max": 1.425901174545288, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71082.65625, "min": 67788.4140625, "max": 77583.515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.64606741573034, "min": 81.0623973727422, "max": 415.07438016528926, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49473.0, "min": 49201.0, "max": 50224.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999915.0, "min": 49996.0, "max": 1999915.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999915.0, "min": 49996.0, "max": 1999915.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.426964521408081, "min": 0.033998556435108185, "max": 2.4894769191741943, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1295.9990234375, "min": 4.079826831817627, "max": 1427.24267578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6992647119898923, "min": 1.7371351604660352, "max": 3.9430878882606826, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1975.4073562026024, "min": 208.45621925592422, "max": 2203.3206137418747, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6992647119898923, "min": 1.7371351604660352, "max": 3.9430878882606826, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1975.4073562026024, "min": 208.45621925592422, "max": 2203.3206137418747, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01750385323074523, "min": 0.013080101381153024, "max": 0.019419481636759883, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0525115596922357, "min": 0.02616020276230605, "max": 0.056405463318030036, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05407169606122706, "min": 0.02354471972212195, "max": 0.06217600256204606, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1622150881836812, "min": 0.0470894394442439, "max": 0.18652800768613817, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3782488739500015e-06, "min": 3.3782488739500015e-06, "max": 0.00029531535156155004, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0134746621850005e-05, "min": 1.0134746621850005e-05, "max": 0.00084411196862935, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112605000000004, "min": 0.10112605000000004, "max": 0.19843844999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033781500000001, "min": 0.20745134999999998, "max": 0.58137065, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.618989500000004e-05, "min": 6.618989500000004e-05, "max": 0.0049220786549999986, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019856968500000014, "min": 0.00019856968500000014, "max": 0.014070395434999999, "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": "1709130601", "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": "1709135102" }, "total": 4500.603398859, "count": 1, "self": 0.654070731999127, "children": { "run_training.setup": { "total": 0.06800933299996359, "count": 1, "self": 0.06800933299996359 }, "TrainerController.start_learning": { "total": 4499.881318794, "count": 1, "self": 8.593499815141513, "children": { "TrainerController._reset_env": { "total": 4.232018402999984, "count": 1, "self": 4.232018402999984 }, "TrainerController.advance": { "total": 4486.907799167859, "count": 232016, "self": 8.698410602595686, "children": { "env_step": { "total": 2985.8413910151485, "count": 232016, "self": 2503.0572803756463, "children": { "SubprocessEnvManager._take_step": { "total": 477.05502440162854, "count": 232016, "self": 32.82385873275416, "children": { "TorchPolicy.evaluate": { "total": 444.2311656688744, "count": 222980, "self": 444.2311656688744 } } }, "workers": { "total": 5.7290862378736165, "count": 232016, "self": 0.0, "children": { "worker_root": { "total": 4484.51411096004, "count": 232016, "is_parallel": true, "self": 2480.7455054741845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016427249997832405, "count": 1, "is_parallel": true, "self": 0.0004237979997014918, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012189270000817487, "count": 2, "is_parallel": true, "self": 0.0012189270000817487 } } }, "UnityEnvironment.step": { "total": 0.0387870170000042, "count": 1, "is_parallel": true, "self": 0.0004798810000465892, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023032300009617757, "count": 1, "is_parallel": true, "self": 0.00023032300009617757 }, "communicator.exchange": { "total": 0.037095563999855585, "count": 1, "is_parallel": true, "self": 0.037095563999855585 }, "steps_from_proto": { "total": 0.000981249000005846, "count": 1, "is_parallel": true, "self": 0.0002562560000569647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007249929999488813, "count": 2, "is_parallel": true, "self": 0.0007249929999488813 } } } } } } }, "UnityEnvironment.step": { "total": 2003.7686054858555, "count": 232015, "is_parallel": true, "self": 66.29917483466966, "children": { "UnityEnvironment._generate_step_input": { "total": 97.2292071431093, "count": 232015, "is_parallel": true, "self": 97.2292071431093 }, "communicator.exchange": { "total": 1698.954846373068, "count": 232015, "is_parallel": true, "self": 1698.954846373068 }, "steps_from_proto": { "total": 141.2853771350085, "count": 232015, "is_parallel": true, "self": 44.39387556589668, "children": { "_process_rank_one_or_two_observation": { "total": 96.89150156911182, "count": 464030, "is_parallel": true, "self": 96.89150156911182 } } } } } } } } } } }, "trainer_advance": { "total": 1492.367997550115, "count": 232016, "self": 13.941868421079334, "children": { "process_trajectory": { "total": 244.61384454203903, "count": 232016, "self": 243.36313126303753, "children": { "RLTrainer._checkpoint": { "total": 1.250713279001502, "count": 10, "self": 1.250713279001502 } } }, "_update_policy": { "total": 1233.8122845869966, "count": 97, "self": 326.7653102249931, "children": { "TorchPPOOptimizer.update": { "total": 907.0469743620035, "count": 2910, "self": 907.0469743620035 } } } } } } }, "trainer_threads": { "total": 1.0510002539376728e-06, "count": 1, "self": 1.0510002539376728e-06 }, "TrainerController._save_models": { "total": 0.14800035700045555, "count": 1, "self": 0.006921168001099431, "children": { "RLTrainer._checkpoint": { "total": 0.14107918899935612, "count": 1, "self": 0.14107918899935612 } } } } } } }