{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40321683883667, "min": 1.403206467628479, "max": 1.4260244369506836, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69582.71875, "min": 68664.4296875, "max": 76640.515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.88594704684317, "min": 91.13162705667276, "max": 402.2741935483871, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49044.0, "min": 48939.0, "max": 50185.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999971.0, "min": 49786.0, "max": 1999971.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999971.0, "min": 49786.0, "max": 1999971.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3768465518951416, "min": 0.13894827663898468, "max": 2.4537532329559326, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1167.0316162109375, "min": 17.09063720703125, "max": 1290.2216796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.621686760252702, "min": 1.8665355785590847, "max": 3.9527495832412276, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1778.2481992840767, "min": 229.5838761627674, "max": 1969.9246737957, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.621686760252702, "min": 1.8665355785590847, "max": 3.9527495832412276, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1778.2481992840767, "min": 229.5838761627674, "max": 1969.9246737957, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018836215060703883, "min": 0.013597009957690413, "max": 0.018836215060703883, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.037672430121407766, "min": 0.027194019915380827, "max": 0.05566413083579391, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05237802012513081, "min": 0.021196152611325188, "max": 0.05668410814056794, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10475604025026163, "min": 0.042392305222650375, "max": 0.16874948851764202, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.5974484675499895e-06, "min": 4.5974484675499895e-06, "max": 0.00029533980155339987, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.194896935099979e-06, "min": 9.194896935099979e-06, "max": 0.0008441025186324998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10153244999999998, "min": 0.10153244999999998, "max": 0.19844660000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20306489999999996, "min": 0.20306489999999996, "max": 0.5813674999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.646925499999984e-05, "min": 8.646925499999984e-05, "max": 0.00492248534, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017293850999999967, "min": 0.00017293850999999967, "max": 0.014070238249999999, "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": "1752298129", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752300476" }, "total": 2346.9782913480003, "count": 1, "self": 0.4435738520005543, "children": { "run_training.setup": { "total": 0.028972182000188695, "count": 1, "self": 0.028972182000188695 }, "TrainerController.start_learning": { "total": 2346.505745314, "count": 1, "self": 4.1670639623189345, "children": { "TrainerController._reset_env": { "total": 3.7783338890001232, "count": 1, "self": 3.7783338890001232 }, "TrainerController.advance": { "total": 2338.45947599068, "count": 231579, "self": 4.407018870548654, "children": { "env_step": { "total": 1874.289214767124, "count": 231579, "self": 1485.1989622032556, "children": { "SubprocessEnvManager._take_step": { "total": 386.5613547600715, "count": 231579, "self": 14.857847440059231, "children": { "TorchPolicy.evaluate": { "total": 371.70350732001225, "count": 222978, "self": 371.70350732001225 } } }, "workers": { "total": 2.528897803796781, "count": 231579, "self": 0.0, "children": { "worker_root": { "total": 2339.3923401869893, "count": 231579, "is_parallel": true, "self": 1125.5031114318879, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010692920000110462, "count": 1, "is_parallel": true, "self": 0.0002671480001481541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008021439998628921, "count": 2, "is_parallel": true, "self": 0.0008021439998628921 } } }, "UnityEnvironment.step": { "total": 0.02809785399995235, "count": 1, "is_parallel": true, "self": 0.00031817700005376537, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018989999989571515, "count": 1, "is_parallel": true, "self": 0.00018989999989571515 }, "communicator.exchange": { "total": 0.02690099899996312, "count": 1, "is_parallel": true, "self": 0.02690099899996312 }, "steps_from_proto": { "total": 0.000688778000039747, "count": 1, "is_parallel": true, "self": 0.00018221599975731806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005065620002824289, "count": 2, "is_parallel": true, "self": 0.0005065620002824289 } } } } } } }, "UnityEnvironment.step": { "total": 1213.8892287551014, "count": 231578, "is_parallel": true, "self": 36.67961552799807, "children": { "UnityEnvironment._generate_step_input": { "total": 78.04366386195966, "count": 231578, "is_parallel": true, "self": 78.04366386195966 }, "communicator.exchange": { "total": 1014.0464738921291, "count": 231578, "is_parallel": true, "self": 1014.0464738921291 }, "steps_from_proto": { "total": 85.11947547301452, "count": 231578, "is_parallel": true, "self": 29.857726246799757, "children": { "_process_rank_one_or_two_observation": { "total": 55.26174922621476, "count": 463156, "is_parallel": true, "self": 55.26174922621476 } } } } } } } } } } }, "trainer_advance": { "total": 459.7632423530074, "count": 231579, "self": 6.312692431945834, "children": { "process_trajectory": { "total": 149.00918914006047, "count": 231579, "self": 147.81488956306043, "children": { "RLTrainer._checkpoint": { "total": 1.194299577000038, "count": 10, "self": 1.194299577000038 } } }, "_update_policy": { "total": 304.4413607810011, "count": 96, "self": 242.38364769299483, "children": { "TorchPPOOptimizer.update": { "total": 62.05771308800627, "count": 2880, "self": 62.05771308800627 } } } } } } }, "trainer_threads": { "total": 8.730003173695877e-07, "count": 1, "self": 8.730003173695877e-07 }, "TrainerController._save_models": { "total": 0.10087059900070017, "count": 1, "self": 0.001734076001412177, "children": { "RLTrainer._checkpoint": { "total": 0.09913652299928799, "count": 1, "self": 0.09913652299928799 } } } } } } }