{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.28861141204834, "min": 3.28861141204834, "max": 3.28861141204834, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 167114.078125, "min": 167114.078125, "max": 167114.078125, "count": 1 }, "SoccerTwos.Step.mean": { "value": 49992.0, "min": 49992.0, "max": 49992.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 49992.0, "min": 49992.0, "max": 49992.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04664747416973114, "min": -0.04664747416973114, "max": -0.04664747416973114, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -37.55121612548828, "min": -37.55121612548828, "max": -37.55121612548828, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 680.4615384615385, "min": 680.4615384615385, "max": 680.4615384615385, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 35384.0, "min": 35384.0, "max": 35384.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1538040835068238, "min": -0.1538040835068238, "max": -0.1538040835068238, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.536400091834366, "min": -7.536400091834366, "max": -7.536400091834366, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.024097790450336602, "min": 0.024097790450336602, "max": 0.024097790450336602, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.09639116180134641, "min": 0.09639116180134641, "max": 0.09639116180134641, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.004554485898486085, "min": 0.004554485898486085, "max": 0.004554485898486085, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.01821794359394434, "min": 0.01821794359394434, "max": 0.01821794359394434, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00028378080540639996, "min": 0.00028378080540639996, "max": 0.00028378080540639996, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0011351232216255999, "min": 0.0011351232216255999, "max": 0.0011351232216255999, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19459360000000003, "min": 0.19459360000000003, "max": 0.19459360000000003, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.7783744000000001, "min": 0.7783744000000001, "max": 0.7783744000000001, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.00473022064, "min": 0.00473022064, "max": 0.00473022064, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.01892088256, "min": 0.01892088256, "max": 0.01892088256, "count": 1 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675372656", "python_version": "3.9.15 | packaged by conda-forge | (main, Nov 22 2022, 15:55:03) \n[GCC 10.4.0]", "command_line_arguments": "/home/chqma/miniconda3/envs/deep-rl-class/bin/mlagents-learn --env env/SoccerTwos.x86_64 --run-id SoccerTwoNoob --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu116", "numpy_version": "1.21.2", "end_time_seconds": "1675372731" }, "total": 74.682307821, "count": 1, "self": 0.8319700518622994, "children": { "run_training.setup": { "total": 0.06310874409973621, "count": 1, "self": 0.06310874409973621 }, "TrainerController.start_learning": { "total": 73.78722902503796, "count": 1, "self": 0.04308897606097162, "children": { "TrainerController._reset_env": { "total": 13.511931366054341, "count": 1, "self": 13.511931366054341 }, "TrainerController.advance": { "total": 60.019109091954306, "count": 1700, "self": 0.045641845325008035, "children": { "env_step": { "total": 47.79579831380397, "count": 1700, "self": 28.610118641983718, "children": { "SubprocessEnvManager._take_step": { "total": 19.16125621739775, "count": 1700, "self": 0.33658020361326635, "children": { "TorchPolicy.evaluate": { "total": 18.824676013784483, "count": 3382, "self": 18.824676013784483 } } }, "workers": { "total": 0.02442345442250371, "count": 1699, "self": 0.0, "children": { "worker_root": { "total": 73.52732781507075, "count": 1699, "is_parallel": true, "self": 49.04900621203706, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003357724752277136, "count": 2, "is_parallel": true, "self": 0.0007940926589071751, "children": { "_process_rank_one_or_two_observation": { "total": 0.002563632093369961, "count": 8, "is_parallel": true, "self": 0.002563632093369961 } } }, "UnityEnvironment.step": { "total": 0.029613188933581114, "count": 1, "is_parallel": true, "self": 0.0005166023038327694, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005972939543426037, "count": 1, "is_parallel": true, "self": 0.0005972939543426037 }, "communicator.exchange": { "total": 0.02727773878723383, "count": 1, "is_parallel": true, "self": 0.02727773878723383 }, "steps_from_proto": { "total": 0.0012215538881719112, "count": 2, "is_parallel": true, "self": 0.00025736214593052864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009641917422413826, "count": 8, "is_parallel": true, "self": 0.0009641917422413826 } } } } } } }, "UnityEnvironment.step": { "total": 24.47832160303369, "count": 1698, "is_parallel": true, "self": 0.8902672145050019, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5213648341596127, "count": 1698, "is_parallel": true, "self": 0.5213648341596127 }, "communicator.exchange": { "total": 20.780624280218035, "count": 1698, "is_parallel": true, "self": 20.780624280218035 }, "steps_from_proto": { "total": 2.286065274151042, "count": 3396, "is_parallel": true, "self": 0.4619027238804847, "children": { "_process_rank_one_or_two_observation": { "total": 1.8241625502705574, "count": 13584, "is_parallel": true, "self": 1.8241625502705574 } } } } } } } } } } }, "trainer_advance": { "total": 12.177668932825327, "count": 1699, "self": 0.0571767664514482, "children": { "process_trajectory": { "total": 4.450284005375579, "count": 1699, "self": 4.450284005375579 }, "_update_policy": { "total": 7.6702081609983, "count": 4, "self": 4.2866214227396995, "children": { "TorchPPOOptimizer.update": { "total": 3.3835867382586002, "count": 123, "self": 3.3835867382586002 } } } } } } }, "trainer_threads": { "total": 1.0889489203691483e-06, "count": 1, "self": 1.0889489203691483e-06 }, "TrainerController._save_models": { "total": 0.21309850201942027, "count": 1, "self": 0.03638885193504393, "children": { "RLTrainer._checkpoint": { "total": 0.17670965008437634, "count": 1, "self": 0.17670965008437634 } } } } } } }