{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4080924987792969, "min": 1.4080924987792969, "max": 1.430686593055725, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71483.2265625, "min": 68847.390625, "max": 76636.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 114.4041570438799, "min": 96.13102119460501, "max": 390.2890625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49537.0, "min": 49022.0, "max": 50109.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49810.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49810.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2478084564208984, "min": 0.14951196312904358, "max": 2.4216086864471436, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 973.301025390625, "min": 18.988019943237305, "max": 1224.42041015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.289234173215289, "min": 1.672017301161458, "max": 3.8664374621141526, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1424.2383970022202, "min": 212.3461972475052, "max": 1931.1665524840355, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.289234173215289, "min": 1.672017301161458, "max": 3.8664374621141526, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1424.2383970022202, "min": 212.3461972475052, "max": 1931.1665524840355, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014712641094502033, "min": 0.01237007464709071, "max": 0.020402013269227203, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.029425282189004066, "min": 0.02474014929418142, "max": 0.061206039807681606, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04250564631074667, "min": 0.020303797349333762, "max": 0.05977942192306121, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08501129262149335, "min": 0.040607594698667523, "max": 0.1683449978629748, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.605848464749997e-06, "min": 4.605848464749997e-06, "max": 0.00029529825156724993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.211696929499995e-06, "min": 9.211696929499995e-06, "max": 0.00084402706865765, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10153525, "min": 0.10153525, "max": 0.19843274999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2030705, "min": 0.2030705, "max": 0.58134235, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.660897499999999e-05, "min": 8.660897499999999e-05, "max": 0.0049217942250000014, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017321794999999998, "min": 0.00017321794999999998, "max": 0.014068983265, "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": "1713813709", "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": "1713816261" }, "total": 2552.2865961750003, "count": 1, "self": 0.44094116200039934, "children": { "run_training.setup": { "total": 0.057842823999976645, "count": 1, "self": 0.057842823999976645 }, "TrainerController.start_learning": { "total": 2551.787812189, "count": 1, "self": 4.6710340049367005, "children": { "TrainerController._reset_env": { "total": 2.8135545939999247, "count": 1, "self": 2.8135545939999247 }, "TrainerController.advance": { "total": 2544.184730139063, "count": 231459, "self": 4.882486351129955, "children": { "env_step": { "total": 2065.7983639419285, "count": 231459, "self": 1713.1352393370598, "children": { "SubprocessEnvManager._take_step": { "total": 349.4850126999761, "count": 231459, "self": 17.190669467944645, "children": { "TorchPolicy.evaluate": { "total": 332.29434323203145, "count": 223066, "self": 332.29434323203145 } } }, "workers": { "total": 3.178111904892603, "count": 231459, "self": 0.0, "children": { "worker_root": { "total": 2544.084765922948, "count": 231459, "is_parallel": true, "self": 1165.353655024886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000961352999979681, "count": 1, "is_parallel": true, "self": 0.00028754100003425265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006738119999454284, "count": 2, "is_parallel": true, "self": 0.0006738119999454284 } } }, "UnityEnvironment.step": { "total": 0.029395132999979978, "count": 1, "is_parallel": true, "self": 0.000417716000015389, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002118579999432768, "count": 1, "is_parallel": true, "self": 0.0002118579999432768 }, "communicator.exchange": { "total": 0.027997108000022308, "count": 1, "is_parallel": true, "self": 0.027997108000022308 }, "steps_from_proto": { "total": 0.0007684509999990041, "count": 1, "is_parallel": true, "self": 0.00020844599998781632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005600050000111878, "count": 2, "is_parallel": true, "self": 0.0005600050000111878 } } } } } } }, "UnityEnvironment.step": { "total": 1378.731110898062, "count": 231458, "is_parallel": true, "self": 40.945936521151, "children": { "UnityEnvironment._generate_step_input": { "total": 89.97019166393102, "count": 231458, "is_parallel": true, "self": 89.97019166393102 }, "communicator.exchange": { "total": 1150.7577329448995, "count": 231458, "is_parallel": true, "self": 1150.7577329448995 }, "steps_from_proto": { "total": 97.0572497680804, "count": 231458, "is_parallel": true, "self": 37.124023190024104, "children": { "_process_rank_one_or_two_observation": { "total": 59.93322657805629, "count": 462916, "is_parallel": true, "self": 59.93322657805629 } } } } } } } } } } }, "trainer_advance": { "total": 473.50387984600457, "count": 231459, "self": 7.245996819973357, "children": { "process_trajectory": { "total": 159.587421613032, "count": 231459, "self": 158.26362521203157, "children": { "RLTrainer._checkpoint": { "total": 1.3237964010004362, "count": 10, "self": 1.3237964010004362 } } }, "_update_policy": { "total": 306.6704614129992, "count": 96, "self": 245.18803484699254, "children": { "TorchPPOOptimizer.update": { "total": 61.482426566006666, "count": 2880, "self": 61.482426566006666 } } } } } } }, "trainer_threads": { "total": 1.018000148178544e-06, "count": 1, "self": 1.018000148178544e-06 }, "TrainerController._save_models": { "total": 0.11849243300002854, "count": 1, "self": 0.0019342909999977564, "children": { "RLTrainer._checkpoint": { "total": 0.11655814200003078, "count": 1, "self": 0.11655814200003078 } } } } } } }