{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403698205947876, "min": 1.403698205947876, "max": 1.426397681236267, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70836.2265625, "min": 68319.8984375, "max": 77181.40625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.96309314586995, "min": 81.4168039538715, "max": 399.024, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49482.0, "min": 48934.0, "max": 50343.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999996.0, "min": 49285.0, "max": 1999996.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999996.0, "min": 49285.0, "max": 1999996.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.473507881164551, "min": 0.029038844630122185, "max": 2.473507881164551, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1407.426025390625, "min": 3.6008167266845703, "max": 1455.595947265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9576846668087535, "min": 1.7310243902667877, "max": 3.9615603506565096, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2251.9225754141808, "min": 214.64702439308167, "max": 2262.1468485593796, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9576846668087535, "min": 1.7310243902667877, "max": 3.9615603506565096, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2251.9225754141808, "min": 214.64702439308167, "max": 2262.1468485593796, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01616335537336353, "min": 0.014048661048097225, "max": 0.020281596363282816, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04849006612009058, "min": 0.028887057982835057, "max": 0.060844789089848444, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05735036792854468, "min": 0.02340131386493643, "max": 0.062182986674209434, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17205110378563404, "min": 0.04680262772987286, "max": 0.17537654700378577, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7187987604333404e-06, "min": 3.7187987604333404e-06, "max": 0.000295366426544525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.115639628130002e-05, "min": 1.115639628130002e-05, "max": 0.00084423346858885, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123956666666667, "min": 0.10123956666666667, "max": 0.198455475, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037187, "min": 0.20761389999999996, "max": 0.58141115, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.18543766666668e-05, "min": 7.18543766666668e-05, "max": 0.0049229282024999994, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021556313000000043, "min": 0.00021556313000000043, "max": 0.014072416384999998, "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": "1704230236", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704232685" }, "total": 2448.487718896, "count": 1, "self": 0.44930711799952405, "children": { "run_training.setup": { "total": 0.07639996900002188, "count": 1, "self": 0.07639996900002188 }, "TrainerController.start_learning": { "total": 2447.962011809, "count": 1, "self": 4.482529331853584, "children": { "TrainerController._reset_env": { "total": 3.3338520760000847, "count": 1, "self": 3.3338520760000847 }, "TrainerController.advance": { "total": 2440.0313458381465, "count": 232310, "self": 4.692466340934061, "children": { "env_step": { "total": 1940.3171957590034, "count": 232310, "self": 1616.8387649301046, "children": { "SubprocessEnvManager._take_step": { "total": 320.66938683792205, "count": 232310, "self": 17.40820309500782, "children": { "TorchPolicy.evaluate": { "total": 303.2611837429142, "count": 223017, "self": 303.2611837429142 } } }, "workers": { "total": 2.809043990976761, "count": 232310, "self": 0.0, "children": { "worker_root": { "total": 2440.5511753660326, "count": 232310, "is_parallel": true, "self": 1122.2922893700375, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007343149998177978, "count": 1, "is_parallel": true, "self": 0.0001919919995998498, "children": { "_process_rank_one_or_two_observation": { "total": 0.000542323000217948, "count": 2, "is_parallel": true, "self": 0.000542323000217948 } } }, "UnityEnvironment.step": { "total": 0.030484526000009282, "count": 1, "is_parallel": true, "self": 0.00029162900023038674, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019979599983344087, "count": 1, "is_parallel": true, "self": 0.00019979599983344087 }, "communicator.exchange": { "total": 0.029291547999946488, "count": 1, "is_parallel": true, "self": 0.029291547999946488 }, "steps_from_proto": { "total": 0.0007015529999989667, "count": 1, "is_parallel": true, "self": 0.0001784060002592014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005231469997397653, "count": 2, "is_parallel": true, "self": 0.0005231469997397653 } } } } } } }, "UnityEnvironment.step": { "total": 1318.2588859959951, "count": 232309, "is_parallel": true, "self": 41.291230610109096, "children": { "UnityEnvironment._generate_step_input": { "total": 83.81201687402881, "count": 232309, "is_parallel": true, "self": 83.81201687402881 }, "communicator.exchange": { "total": 1102.1914260289318, "count": 232309, "is_parallel": true, "self": 1102.1914260289318 }, "steps_from_proto": { "total": 90.9642124829254, "count": 232309, "is_parallel": true, "self": 31.89295480597457, "children": { "_process_rank_one_or_two_observation": { "total": 59.071257676950836, "count": 464618, "is_parallel": true, "self": 59.071257676950836 } } } } } } } } } } }, "trainer_advance": { "total": 495.0216837382093, "count": 232310, "self": 6.724026604289747, "children": { "process_trajectory": { "total": 152.04046322692147, "count": 232310, "self": 150.84634245792154, "children": { "RLTrainer._checkpoint": { "total": 1.1941207689999374, "count": 10, "self": 1.1941207689999374 } } }, "_update_policy": { "total": 336.25719390699805, "count": 97, "self": 271.6657796699981, "children": { "TorchPPOOptimizer.update": { "total": 64.59141423699998, "count": 2910, "self": 64.59141423699998 } } } } } } }, "trainer_threads": { "total": 1.0069998097606003e-06, "count": 1, "self": 1.0069998097606003e-06 }, "TrainerController._save_models": { "total": 0.11428355599991846, "count": 1, "self": 0.00209052399986831, "children": { "RLTrainer._checkpoint": { "total": 0.11219303200005015, "count": 1, "self": 0.11219303200005015 } } } } } } }