{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6701158285140991, "min": 1.6587228775024414, "max": 3.29573130607605, "count": 725 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30516.357421875, "min": 16613.8046875, "max": 178980.65625, "count": 725 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.282828282828284, "min": 35.595588235294116, "max": 999.0, "count": 725 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19516.0, "min": 12772.0, "max": 28016.0, "count": 725 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1557.265374110577, "min": 1198.5330205252608, "max": 1588.0020185317587, "count": 680 }, "SoccerTwos.Self-play.ELO.sum": { "value": 308338.54407389427, "min": 2399.1962815952575, "max": 409448.62126481585, "count": 680 }, "SoccerTwos.Step.mean": { "value": 7249992.0, "min": 9026.0, "max": 7249992.0, "count": 725 }, "SoccerTwos.Step.sum": { "value": 7249992.0, "min": 9026.0, "max": 7249992.0, "count": 725 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.026756681501865387, "min": -0.12756748497486115, "max": 0.17237921059131622, "count": 725 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.297822952270508, "min": -24.875659942626953, "max": 30.08611488342285, "count": 725 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01810976304113865, "min": -0.1257050484418869, "max": 0.16898171603679657, "count": 725 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.58573317527771, "min": -24.512483596801758, "max": 29.562793731689453, "count": 725 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 725 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 725 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0841818174930534, "min": -0.6153846153846154, "max": 0.5067600041627884, "count": 725 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 16.667999863624573, "min": -52.45539999008179, "max": 65.7007999420166, "count": 725 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0841818174930534, "min": -0.6153846153846154, "max": 0.5067600041627884, "count": 725 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 16.667999863624573, "min": -52.45539999008179, "max": 65.7007999420166, "count": 725 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 725 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 725 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018028397635013484, "min": 0.010461795031248281, "max": 0.024881355188942203, "count": 348 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018028397635013484, "min": 0.010461795031248281, "max": 0.024881355188942203, "count": 348 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10629347438613573, "min": 1.589391454596504e-07, "max": 0.12507142946124078, "count": 348 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10629347438613573, "min": 1.589391454596504e-07, "max": 0.12507142946124078, "count": 348 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10934197281797726, "min": 1.9186231270396092e-07, "max": 0.1278058871626854, "count": 348 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10934197281797726, "min": 1.9186231270396092e-07, "max": 0.1278058871626854, "count": 348 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 348 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 348 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 348 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 348 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 348 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 348 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727173758", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727190579" }, "total": 16820.303834783, "count": 1, "self": 0.13345043200388318, "children": { "run_training.setup": { "total": 0.051617436000015005, "count": 1, "self": 0.051617436000015005 }, "TrainerController.start_learning": { "total": 16820.118766915, "count": 1, "self": 11.377075497650367, "children": { "TrainerController._reset_env": { "total": 4.294128538998052, "count": 37, "self": 4.294128538998052 }, "TrainerController.advance": { "total": 16804.151323784354, "count": 498753, "self": 12.082525273013744, "children": { "env_step": { "total": 12949.70809076626, "count": 498753, "self": 9456.580573319003, "children": { "SubprocessEnvManager._take_step": { "total": 3486.655585516228, "count": 498753, "self": 77.85140495581027, "children": { "TorchPolicy.evaluate": { "total": 3408.8041805604175, "count": 916844, "self": 3408.8041805604175 } } }, "workers": { "total": 6.4719319310295305, "count": 498752, "self": 0.0, "children": { "worker_root": { "total": 16792.618799273245, "count": 498752, "is_parallel": true, "self": 8834.781746554789, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003693558000009034, "count": 2, "is_parallel": true, "self": 0.0009371319999900152, "children": { "_process_rank_one_or_two_observation": { "total": 0.002756426000019019, "count": 8, "is_parallel": true, "self": 0.002756426000019019 } } }, "UnityEnvironment.step": { "total": 0.03822099900003195, "count": 1, "is_parallel": true, "self": 0.0010993349999353086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007964679999759028, "count": 1, "is_parallel": true, "self": 0.0007964679999759028 }, "communicator.exchange": { "total": 0.0329992660000471, "count": 1, "is_parallel": true, "self": 0.0329992660000471 }, "steps_from_proto": { "total": 0.0033259300000736403, "count": 2, "is_parallel": true, "self": 0.0005812719999767069, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027446580000969334, "count": 8, "is_parallel": true, "self": 0.0027446580000969334 } } } } } } }, "UnityEnvironment.step": { "total": 7957.752285106464, "count": 498751, "is_parallel": true, "self": 488.25413560435663, "children": { "UnityEnvironment._generate_step_input": { "total": 330.8674484480965, "count": 498751, "is_parallel": true, "self": 330.8674484480965 }, "communicator.exchange": { "total": 5602.609950587758, "count": 498751, "is_parallel": true, "self": 5602.609950587758 }, "steps_from_proto": { "total": 1536.020750466253, "count": 997502, "is_parallel": true, "self": 259.1321704771001, "children": { "_process_rank_one_or_two_observation": { "total": 1276.888579989153, "count": 3990008, "is_parallel": true, "self": 1276.888579989153 } } } } }, "steps_from_proto": { "total": 0.0847676119915377, "count": 72, "is_parallel": true, "self": 0.01620631099444836, "children": { "_process_rank_one_or_two_observation": { "total": 0.06856130099708935, "count": 288, "is_parallel": true, "self": 0.06856130099708935 } } } } } } } } }, "trainer_advance": { "total": 3842.3607077450783, "count": 498752, "self": 90.9317398571734, "children": { "process_trajectory": { "total": 1775.0596767289287, "count": 498752, "self": 1771.9084069749326, "children": { "RLTrainer._checkpoint": { "total": 3.1512697539960755, "count": 14, "self": 3.1512697539960755 } } }, "_update_policy": { "total": 1976.369291158976, "count": 348, "self": 1168.7769840309502, "children": { "TorchPOCAOptimizer.update": { "total": 807.5923071280258, "count": 10440, "self": 807.5923071280258 } } } } } } }, "trainer_threads": { "total": 1.5949990483932197e-06, "count": 1, "self": 1.5949990483932197e-06 }, "TrainerController._save_models": { "total": 0.29623749899838003, "count": 1, "self": 0.0029462849997798912, "children": { "RLTrainer._checkpoint": { "total": 0.29329121399860014, "count": 1, "self": 0.29329121399860014 } } } } } } }