{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1711854934692383, "min": 2.1563897132873535, "max": 3.2957355976104736, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42728.9296875, "min": 23495.42578125, "max": 175875.5625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.525252525252526, "min": 43.823008849557525, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19612.0, "min": 9336.0, "max": 31280.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1540.2993140960302, "min": 1198.7578908373744, "max": 1544.704477868567, "count": 438 }, "SoccerTwos.Self-play.ELO.sum": { "value": 304979.264191014, "min": 2398.090458690257, "max": 317065.89189016435, "count": 438 }, "SoccerTwos.Step.mean": { "value": 4999953.0, "min": 9658.0, "max": 4999953.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999953.0, "min": 9658.0, "max": 4999953.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013220873661339283, "min": -0.09213639795780182, "max": 0.15115022659301758, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.630953788757324, "min": -12.852289199829102, "max": 25.426095962524414, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01672838069498539, "min": -0.08740000426769257, "max": 0.155443474650383, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.3289477825164795, "min": -12.370573997497559, "max": 24.560070037841797, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11635577918297083, "min": -0.5985568609892153, "max": 0.4048774184719209, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -23.154800057411194, "min": -45.24959981441498, "max": 56.15120041370392, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11635577918297083, "min": -0.5985568609892153, "max": 0.4048774184719209, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -23.154800057411194, "min": -45.24959981441498, "max": 56.15120041370392, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013198242879783113, "min": 0.009880509349750355, "max": 0.02463163676826904, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013198242879783113, "min": 0.009880509349750355, "max": 0.02463163676826904, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09781300127506257, "min": 2.4730725461571033e-06, "max": 0.09896448229749998, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09781300127506257, "min": 2.4730725461571033e-06, "max": 0.09896448229749998, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09977005993326506, "min": 3.096013002353478e-06, "max": 0.10238260130087534, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09977005993326506, "min": 3.096013002353478e-06, "max": 0.10238260130087534, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714442506", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\User\\miniconda3\\envs\\mlagents2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_o", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714450780" }, "total": 8274.125010300006, "count": 1, "self": 0.27465900001698174, "children": { "run_training.setup": { "total": 0.07673349999822676, "count": 1, "self": 0.07673349999822676 }, "TrainerController.start_learning": { "total": 8273.77361779999, "count": 1, "self": 6.667253402309143, "children": { "TrainerController._reset_env": { "total": 9.418485800008057, "count": 25, "self": 9.418485800008057 }, "TrainerController.advance": { "total": 8257.526057797673, "count": 334358, "self": 6.226081602231716, "children": { "env_step": { "total": 6328.019722297337, "count": 334358, "self": 3447.482715898863, "children": { "SubprocessEnvManager._take_step": { "total": 2876.5351900991664, "count": 334358, "self": 37.89492169872392, "children": { "TorchPolicy.evaluate": { "total": 2838.6402684004424, "count": 638696, "self": 2838.6402684004424 } } }, "workers": { "total": 4.001816299307393, "count": 334358, "self": 0.0, "children": { "worker_root": { "total": 8259.125867002265, "count": 334358, "is_parallel": true, "self": 5548.283452111122, "children": { "steps_from_proto": { "total": 0.03645219997270033, "count": 50, "is_parallel": true, "self": 0.007609000036609359, "children": { "_process_rank_one_or_two_observation": { "total": 0.02884319993609097, "count": 200, "is_parallel": true, "self": 0.02884319993609097 } } }, "UnityEnvironment.step": { "total": 2710.805962691171, "count": 334358, "is_parallel": true, "self": 137.25417298832326, "children": { "UnityEnvironment._generate_step_input": { "total": 118.47085500140383, "count": 334358, "is_parallel": true, "self": 118.47085500140383 }, "communicator.exchange": { "total": 1996.3595591027843, "count": 334358, "is_parallel": true, "self": 1996.3595591027843 }, "steps_from_proto": { "total": 458.7213755986595, "count": 668716, "is_parallel": true, "self": 95.8600013062096, "children": { "_process_rank_one_or_two_observation": { "total": 362.8613742924499, "count": 2674864, "is_parallel": true, "self": 362.8613742924499 } } } } } } } } } } }, "trainer_advance": { "total": 1923.280253898105, "count": 334358, "self": 47.399305700892, "children": { "process_trajectory": { "total": 839.0995808973094, "count": 334358, "self": 837.3124306973041, "children": { "RLTrainer._checkpoint": { "total": 1.7871502000052715, "count": 10, "self": 1.7871502000052715 } } }, "_update_policy": { "total": 1036.7813672999036, "count": 238, "self": 598.8523994003481, "children": { "TorchPOCAOptimizer.update": { "total": 437.9289678995556, "count": 7143, "self": 437.9289678995556 } } } } } } }, "trainer_threads": { "total": 7.999915396794677e-07, "count": 1, "self": 7.999915396794677e-07 }, "TrainerController._save_models": { "total": 0.1618200000084471, "count": 1, "self": 0.00613910001993645, "children": { "RLTrainer._checkpoint": { "total": 0.15568089998851065, "count": 1, "self": 0.15568089998851065 } } } } } } }