{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4058152437210083, "min": 1.4058152437210083, "max": 1.4295692443847656, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70273.890625, "min": 67516.8125, "max": 77439.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.57360406091371, "min": 80.83306055646482, "max": 392.046875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49392.0, "min": 48887.0, "max": 50182.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999947.0, "min": 49560.0, "max": 1999947.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999947.0, "min": 49560.0, "max": 1999947.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.392594575881958, "min": 0.09641305357217789, "max": 2.4227731227874756, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1414.0234375, "min": 12.244458198547363, "max": 1453.478515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.725115331901512, "min": 1.8569767618273187, "max": 3.980361661413214, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2201.5431611537933, "min": 235.83604875206947, "max": 2346.4954919815063, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.725115331901512, "min": 1.8569767618273187, "max": 3.980361661413214, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2201.5431611537933, "min": 235.83604875206947, "max": 2346.4954919815063, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013763395173332861, "min": 0.013320375325889068, "max": 0.020895809721938954, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.041290185519998586, "min": 0.02664513394702226, "max": 0.053633886823081414, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06037468926774131, "min": 0.02265542062620322, "max": 0.06139017647753159, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18112406780322393, "min": 0.04531084125240644, "max": 0.18124895952641965, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.501298832933326e-06, "min": 3.501298832933326e-06, "max": 0.00029535607654797497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0503896498799978e-05, "min": 1.0503896498799978e-05, "max": 0.0008436810187729999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116706666666668, "min": 0.10116706666666668, "max": 0.19845202499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035012, "min": 0.20748895, "max": 0.5812270000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.823662666666655e-05, "min": 6.823662666666655e-05, "max": 0.004922756047500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020470987999999965, "min": 0.00020470987999999965, "max": 0.014063227299999995, "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": "1714091893", "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": "1714094321" }, "total": 2428.112860503, "count": 1, "self": 0.44018132600012905, "children": { "run_training.setup": { "total": 0.05839377199993123, "count": 1, "self": 0.05839377199993123 }, "TrainerController.start_learning": { "total": 2427.614285405, "count": 1, "self": 4.1641894809540645, "children": { "TrainerController._reset_env": { "total": 3.1354484209999782, "count": 1, "self": 3.1354484209999782 }, "TrainerController.advance": { "total": 2420.188434920046, "count": 232208, "self": 4.5442803579258, "children": { "env_step": { "total": 1904.3875748060543, "count": 232208, "self": 1578.387716650106, "children": { "SubprocessEnvManager._take_step": { "total": 323.1647708689486, "count": 232208, "self": 16.959621594900568, "children": { "TorchPolicy.evaluate": { "total": 306.20514927404804, "count": 222914, "self": 306.20514927404804 } } }, "workers": { "total": 2.83508728699951, "count": 232208, "self": 0.0, "children": { "worker_root": { "total": 2420.4876023689626, "count": 232208, "is_parallel": true, "self": 1142.8557308489935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009434160000409975, "count": 1, "is_parallel": true, "self": 0.00023096299992175773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007124530001192397, "count": 2, "is_parallel": true, "self": 0.0007124530001192397 } } }, "UnityEnvironment.step": { "total": 0.048107557999969686, "count": 1, "is_parallel": true, "self": 0.00038606199996138457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020327799995811802, "count": 1, "is_parallel": true, "self": 0.00020327799995811802 }, "communicator.exchange": { "total": 0.0467157609999731, "count": 1, "is_parallel": true, "self": 0.0467157609999731 }, "steps_from_proto": { "total": 0.0008024570000770836, "count": 1, "is_parallel": true, "self": 0.00023713100006261811, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005653260000144655, "count": 2, "is_parallel": true, "self": 0.0005653260000144655 } } } } } } }, "UnityEnvironment.step": { "total": 1277.631871519969, "count": 232207, "is_parallel": true, "self": 39.91510833694542, "children": { "UnityEnvironment._generate_step_input": { "total": 82.37325179609172, "count": 232207, "is_parallel": true, "self": 82.37325179609172 }, "communicator.exchange": { "total": 1063.3211369560613, "count": 232207, "is_parallel": true, "self": 1063.3211369560613 }, "steps_from_proto": { "total": 92.02237443087074, "count": 232207, "is_parallel": true, "self": 32.7924409828172, "children": { "_process_rank_one_or_two_observation": { "total": 59.22993344805354, "count": 464414, "is_parallel": true, "self": 59.22993344805354 } } } } } } } } } } }, "trainer_advance": { "total": 511.25657975606566, "count": 232208, "self": 6.694469548149414, "children": { "process_trajectory": { "total": 151.98494416091557, "count": 232208, "self": 150.6900589229159, "children": { "RLTrainer._checkpoint": { "total": 1.2948852379996652, "count": 10, "self": 1.2948852379996652 } } }, "_update_policy": { "total": 352.5771660470007, "count": 97, "self": 289.4108671480092, "children": { "TorchPPOOptimizer.update": { "total": 63.1662988989915, "count": 2910, "self": 63.1662988989915 } } } } } } }, "trainer_threads": { "total": 1.03899992609513e-06, "count": 1, "self": 1.03899992609513e-06 }, "TrainerController._save_models": { "total": 0.1262115439999434, "count": 1, "self": 0.0023781089998919924, "children": { "RLTrainer._checkpoint": { "total": 0.1238334350000514, "count": 1, "self": 0.1238334350000514 } } } } } } }