{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4083560705184937, "min": 1.4083560705184937, "max": 1.4304262399673462, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69974.171875, "min": 67264.5625, "max": 77501.7578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 110.06681514476615, "min": 91.04096834264432, "max": 409.2520325203252, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49420.0, "min": 48864.0, "max": 50338.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999909.0, "min": 49885.0, "max": 1999909.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999909.0, "min": 49885.0, "max": 1999909.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.336402177810669, "min": 0.010859047994017601, "max": 2.4235692024230957, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1049.0445556640625, "min": 1.3248038291931152, "max": 1291.9776611328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.519974739620574, "min": 1.6862260840955328, "max": 3.8304605906934532, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1580.4686580896378, "min": 205.719582259655, "max": 2002.9133558571339, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.519974739620574, "min": 1.6862260840955328, "max": 3.8304605906934532, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1580.4686580896378, "min": 205.719582259655, "max": 2002.9133558571339, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017674006724135122, "min": 0.012898803724844279, "max": 0.021337292034877463, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05302202017240537, "min": 0.025797607449688557, "max": 0.06205983057540531, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04916503375603093, "min": 0.02210560841485858, "max": 0.07417824847830666, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1474951012680928, "min": 0.04421121682971716, "max": 0.22253474543492, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1721989426333325e-06, "min": 3.1721989426333325e-06, "max": 0.00029535442654852497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.516596827899998e-06, "min": 9.516596827899998e-06, "max": 0.0008441836686054497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105736666666665, "min": 0.10105736666666665, "max": 0.19845147500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30317209999999994, "min": 0.20724129999999996, "max": 0.5813945500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.276259666666667e-05, "min": 6.276259666666667e-05, "max": 0.004922728602499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018828779, "min": 0.00018828779, "max": 0.014071588045000001, "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": "1740041841", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740044303" }, "total": 2462.364942156, "count": 1, "self": 0.437250332000076, "children": { "run_training.setup": { "total": 0.0226165380000225, "count": 1, "self": 0.0226165380000225 }, "TrainerController.start_learning": { "total": 2461.905075286, "count": 1, "self": 4.349644490037463, "children": { "TrainerController._reset_env": { "total": 3.095244182999977, "count": 1, "self": 3.095244182999977 }, "TrainerController.advance": { "total": 2454.3314498149625, "count": 231031, "self": 4.505896737016428, "children": { "env_step": { "total": 1980.8417426669516, "count": 231031, "self": 1546.5300932768068, "children": { "SubprocessEnvManager._take_step": { "total": 431.62646183009736, "count": 231031, "self": 15.600386135108636, "children": { "TorchPolicy.evaluate": { "total": 416.0260756949887, "count": 223054, "self": 416.0260756949887 } } }, "workers": { "total": 2.6851875600474955, "count": 231031, "self": 0.0, "children": { "worker_root": { "total": 2454.2459951669493, "count": 231031, "is_parallel": true, "self": 1191.6664728429535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011242090000109783, "count": 1, "is_parallel": true, "self": 0.0004720530000099643, "children": { "_process_rank_one_or_two_observation": { "total": 0.000652156000001014, "count": 2, "is_parallel": true, "self": 0.000652156000001014 } } }, "UnityEnvironment.step": { "total": 0.029257400000005873, "count": 1, "is_parallel": true, "self": 0.0003267519999781143, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019281499999124208, "count": 1, "is_parallel": true, "self": 0.00019281499999124208 }, "communicator.exchange": { "total": 0.028001934000030815, "count": 1, "is_parallel": true, "self": 0.028001934000030815 }, "steps_from_proto": { "total": 0.000735899000005702, "count": 1, "is_parallel": true, "self": 0.0001977189999706752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005381800000350268, "count": 2, "is_parallel": true, "self": 0.0005381800000350268 } } } } } } }, "UnityEnvironment.step": { "total": 1262.579522323996, "count": 231030, "is_parallel": true, "self": 37.65821425190393, "children": { "UnityEnvironment._generate_step_input": { "total": 82.70746142707685, "count": 231030, "is_parallel": true, "self": 82.70746142707685 }, "communicator.exchange": { "total": 1053.7418607969987, "count": 231030, "is_parallel": true, "self": 1053.7418607969987 }, "steps_from_proto": { "total": 88.47198584801646, "count": 231030, "is_parallel": true, "self": 33.11497553488846, "children": { "_process_rank_one_or_two_observation": { "total": 55.357010313128, "count": 462060, "is_parallel": true, "self": 55.357010313128 } } } } } } } } } } }, "trainer_advance": { "total": 468.98381041099424, "count": 231031, "self": 6.82920118496537, "children": { "process_trajectory": { "total": 159.0835814200285, "count": 231031, "self": 157.71353782502808, "children": { "RLTrainer._checkpoint": { "total": 1.3700435950004248, "count": 10, "self": 1.3700435950004248 } } }, "_update_policy": { "total": 303.07102780600036, "count": 97, "self": 238.82953429699938, "children": { "TorchPPOOptimizer.update": { "total": 64.24149350900097, "count": 2910, "self": 64.24149350900097 } } } } } } }, "trainer_threads": { "total": 1.199000053020427e-06, "count": 1, "self": 1.199000053020427e-06 }, "TrainerController._save_models": { "total": 0.12873559899981046, "count": 1, "self": 0.0019624499996098166, "children": { "RLTrainer._checkpoint": { "total": 0.12677314900020065, "count": 1, "self": 0.12677314900020065 } } } } } } }