{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.116776466369629, "min": 2.904965877532959, "max": 3.164104700088501, "count": 95 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39994.4765625, "min": 6307.76171875, "max": 138840.15625, "count": 95 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 923.1666666666666, "min": 532.5, "max": 999.0, "count": 95 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22156.0, "min": 3996.0, "max": 31968.0, "count": 95 }, "SoccerTwos.Step.mean": { "value": 2999150.0, "min": 2009164.0, "max": 2999150.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 2999150.0, "min": 2009164.0, "max": 2999150.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017505554482340813, "min": -0.02135247178375721, "max": 0.009640387259423733, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1925610899925232, "min": -0.3027734160423279, "max": 0.09640387445688248, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01827135495841503, "min": -0.02114020101726055, "max": 0.011215558275580406, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2009848952293396, "min": -0.2993220090866089, "max": 0.11215558648109436, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18181818181818182, "min": -0.5454545454545454, "max": 0.2756857190813337, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -6.310799956321716, "max": 3.859600067138672, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18181818181818182, "min": -0.5454545454545454, "max": 0.2756857190813337, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -6.310799956321716, "max": 3.859600067138672, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015776646292457976, "min": 0.01380585243805399, "max": 0.023726679547689856, "count": 42 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015776646292457976, "min": 0.01380585243805399, "max": 0.023726679547689856, "count": 42 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003983283950947225, "min": 2.4570815979372026e-07, "max": 0.005457229221550127, "count": 42 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003983283950947225, "min": 2.4570815979372026e-07, "max": 0.005457229221550127, "count": 42 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003990688663907349, "min": 2.3202827629612935e-07, "max": 0.0054966877369831005, "count": 42 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003990688663907349, "min": 2.3202827629612935e-07, "max": 0.0054966877369831005, "count": 42 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 42 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 42 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 42 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 42 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 42 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 42 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1193.4744619341584, "min": 1182.8467215275443, "max": 1193.4744619341584, "count": 58 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2386.948923868317, "min": 2365.6934430550887, "max": 14276.792717336062, "count": 58 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677094734", "python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --resume --initialize-from=SoccerTwos --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1677115845" }, "total": 21111.642440923002, "count": 1, "self": 0.7434031670054537, "children": { "run_training.setup": { "total": 0.026563553998130374, "count": 1, "self": 0.026563553998130374 }, "TrainerController.start_learning": { "total": 21110.872474202, "count": 1, "self": 2.530553965974832, "children": { "TrainerController._reset_env": { "total": 3.3131544970019604, "count": 6, "self": 3.3131544970019604 }, "TrainerController.advance": { "total": 21104.62380191203, "count": 64471, "self": 3.0193039232617593, "children": { "env_step": { "total": 17592.576774839523, "count": 64471, "self": 17188.791970257786, "children": { "SubprocessEnvManager._take_step": { "total": 402.1214819888555, "count": 64471, "self": 18.741726848078542, "children": { "TorchPolicy.evaluate": { "total": 383.379755140777, "count": 128142, "self": 383.379755140777 } } }, "workers": { "total": 1.663322592881741, "count": 64471, "self": 0.0, "children": { "worker_root": { "total": 21077.682511608175, "count": 64471, "is_parallel": true, "self": 4249.830887061995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008337165010743774, "count": 2, "is_parallel": true, "self": 0.0018314219996682368, "children": { "_process_rank_one_or_two_observation": { "total": 0.006505743011075538, "count": 8, "is_parallel": true, "self": 0.006505743011075538 } } }, "UnityEnvironment.step": { "total": 0.3917583009970258, "count": 1, "is_parallel": true, "self": 0.0006637920014327392, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0038347719964804128, "count": 1, "is_parallel": true, "self": 0.0038347719964804128 }, "communicator.exchange": { "total": 0.37030163999588694, "count": 1, "is_parallel": true, "self": 0.37030163999588694 }, "steps_from_proto": { "total": 0.016958097003225703, "count": 2, "is_parallel": true, "self": 0.0011376280017429963, "children": { "_process_rank_one_or_two_observation": { "total": 0.015820469001482707, "count": 8, "is_parallel": true, "self": 0.015820469001482707 } } } } } } }, "steps_from_proto": { "total": 0.03470828200079268, "count": 10, "is_parallel": true, "self": 0.006117324985098094, "children": { "_process_rank_one_or_two_observation": { "total": 0.028590957015694585, "count": 40, "is_parallel": true, "self": 0.028590957015694585 } } }, "UnityEnvironment.step": { "total": 16827.81691626418, "count": 64470, "is_parallel": true, "self": 56.63808648326085, "children": { "UnityEnvironment._generate_step_input": { "total": 318.6570585797235, "count": 64470, "is_parallel": true, "self": 318.6570585797235 }, "communicator.exchange": { "total": 15845.212454944936, "count": 64470, "is_parallel": true, "self": 15845.212454944936 }, "steps_from_proto": { "total": 607.3093162562582, "count": 128940, "is_parallel": true, "self": 91.09527064061695, "children": { "_process_rank_one_or_two_observation": { "total": 516.2140456156412, "count": 515760, "is_parallel": true, "self": 516.2140456156412 } } } } } } } } } } }, "trainer_advance": { "total": 3509.0277231492437, "count": 64471, "self": 19.277105356304673, "children": { "process_trajectory": { "total": 431.59148503193865, "count": 64471, "self": 430.6668806779344, "children": { "RLTrainer._checkpoint": { "total": 0.9246043540042592, "count": 2, "self": 0.9246043540042592 } } }, "_update_policy": { "total": 3058.1591327610004, "count": 42, "self": 274.7183453551188, "children": { "TorchPOCAOptimizer.update": { "total": 2783.4407874058816, "count": 1374, "self": 2783.4407874058816 } } } } } } }, "trainer_threads": { "total": 1.1410011211410165e-06, "count": 1, "self": 1.1410011211410165e-06 }, "TrainerController._save_models": { "total": 0.4049626859923592, "count": 1, "self": 0.006110512986197136, "children": { "RLTrainer._checkpoint": { "total": 0.39885217300616205, "count": 1, "self": 0.39885217300616205 } } } } } } }