{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4088613986968994, "min": 1.4088613986968994, "max": 1.42890202999115, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69706.234375, "min": 68588.7109375, "max": 76706.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.65587734241907, "min": 78.88870967741936, "max": 402.088, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49106.0, "min": 48911.0, "max": 50261.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49696.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49696.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.412590742111206, "min": -0.001070452737621963, "max": 2.450330972671509, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1416.1907958984375, "min": -0.13273614645004272, "max": 1483.0888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7433942005012875, "min": 1.8023117237514066, "max": 3.9808995340888207, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2197.372395694256, "min": 223.4866537451744, "max": 2362.2698134183884, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7433942005012875, "min": 1.8023117237514066, "max": 3.9808995340888207, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2197.372395694256, "min": 223.4866537451744, "max": 2362.2698134183884, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016720450219549498, "min": 0.013718927883504269, "max": 0.02127690303216999, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05016135065864849, "min": 0.027437855767008537, "max": 0.05908297306547562, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061391010300980674, "min": 0.023320291377604007, "max": 0.061391010300980674, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18417303090294201, "min": 0.046640582755208014, "max": 0.18417303090294201, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5998988000666644e-06, "min": 3.5998988000666644e-06, "max": 0.000295340476553175, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0799696400199993e-05, "min": 1.0799696400199993e-05, "max": 0.00084414946861685, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119993333333333, "min": 0.10119993333333333, "max": 0.19844682500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035998, "min": 0.20752820000000002, "max": 0.58138315, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.98766733333333e-05, "min": 6.98766733333333e-05, "max": 0.0049224965675, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002096300199999999, "min": 0.0002096300199999999, "max": 0.014071019184999999, "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": "1692094433", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692096814" }, "total": 2380.85135177, "count": 1, "self": 0.7607726040000671, "children": { "run_training.setup": { "total": 0.04233614600002511, "count": 1, "self": 0.04233614600002511 }, "TrainerController.start_learning": { "total": 2380.04824302, "count": 1, "self": 4.202821396966101, "children": { "TrainerController._reset_env": { "total": 4.115225146000057, "count": 1, "self": 4.115225146000057 }, "TrainerController.advance": { "total": 2371.5518494660346, "count": 232378, "self": 4.411337404020742, "children": { "env_step": { "total": 1826.6234119399774, "count": 232378, "self": 1543.362116950818, "children": { "SubprocessEnvManager._take_step": { "total": 280.49006645115753, "count": 232378, "self": 16.6406435052819, "children": { "TorchPolicy.evaluate": { "total": 263.84942294587563, "count": 222882, "self": 263.84942294587563 } } }, "workers": { "total": 2.7712285380017647, "count": 232378, "self": 0.0, "children": { "worker_root": { "total": 2372.6955459539654, "count": 232378, "is_parallel": true, "self": 1112.1983071258662, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008800589999964359, "count": 1, "is_parallel": true, "self": 0.00024046899989116355, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006395900001052723, "count": 2, "is_parallel": true, "self": 0.0006395900001052723 } } }, "UnityEnvironment.step": { "total": 0.028346284999997806, "count": 1, "is_parallel": true, "self": 0.00035227900013978797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021714799993333145, "count": 1, "is_parallel": true, "self": 0.00021714799993333145 }, "communicator.exchange": { "total": 0.027033058000029087, "count": 1, "is_parallel": true, "self": 0.027033058000029087 }, "steps_from_proto": { "total": 0.0007437999998956002, "count": 1, "is_parallel": true, "self": 0.00020314299990786822, "children": { "_process_rank_one_or_two_observation": { "total": 0.000540656999987732, "count": 2, "is_parallel": true, "self": 0.000540656999987732 } } } } } } }, "UnityEnvironment.step": { "total": 1260.4972388280992, "count": 232377, "is_parallel": true, "self": 39.67354965902882, "children": { "UnityEnvironment._generate_step_input": { "total": 79.36679362898212, "count": 232377, "is_parallel": true, "self": 79.36679362898212 }, "communicator.exchange": { "total": 1045.711774872986, "count": 232377, "is_parallel": true, "self": 1045.711774872986 }, "steps_from_proto": { "total": 95.74512066710213, "count": 232377, "is_parallel": true, "self": 33.66841799999338, "children": { "_process_rank_one_or_two_observation": { "total": 62.07670266710875, "count": 464754, "is_parallel": true, "self": 62.07670266710875 } } } } } } } } } } }, "trainer_advance": { "total": 540.5171001220363, "count": 232378, "self": 6.297236983086236, "children": { "process_trajectory": { "total": 136.90357280795024, "count": 232378, "self": 135.45234413194999, "children": { "RLTrainer._checkpoint": { "total": 1.4512286760002553, "count": 10, "self": 1.4512286760002553 } } }, "_update_policy": { "total": 397.3162903309998, "count": 97, "self": 337.42805172499686, "children": { "TorchPPOOptimizer.update": { "total": 59.888238606002915, "count": 2910, "self": 59.888238606002915 } } } } } } }, "trainer_threads": { "total": 1.3289995877130423e-06, "count": 1, "self": 1.3289995877130423e-06 }, "TrainerController._save_models": { "total": 0.17834568199987189, "count": 1, "self": 0.0029280479998305964, "children": { "RLTrainer._checkpoint": { "total": 0.1754176340000413, "count": 1, "self": 0.1754176340000413 } } } } } } }