{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.382171869277954, "min": 1.3406294584274292, "max": 1.5941110849380493, "count": 1844 }, "SoccerTwos.Policy.Entropy.sum": { "value": 24901.208984375, "min": 21594.4140625, "max": 36567.2734375, "count": 1844 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.20588235294117, "min": 44.31818181818182, "max": 104.61702127659575, "count": 1844 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 14520.0, "max": 21788.0, "count": 1844 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1880.319441975431, "min": 1797.6161456333896, "max": 1892.5716559389089, "count": 1844 }, "SoccerTwos.Self-play.ELO.sum": { "value": 255723.4441086586, "min": 175502.58311787687, "max": 410920.08707172686, "count": 1844 }, "SoccerTwos.Step.mean": { "value": 49999984.0, "min": 31569976.0, "max": 49999984.0, "count": 1844 }, "SoccerTwos.Step.sum": { "value": 49999984.0, "min": 31569976.0, "max": 49999984.0, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008061565458774567, "min": -0.13645006716251373, "max": 0.1033400148153305, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.0963728427886963, "min": -24.922229766845703, "max": 16.017702102661133, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.008827511221170425, "min": -0.13706254959106445, "max": 0.10023332387208939, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.2005414962768555, "min": -25.208498001098633, "max": 16.848989486694336, "count": 1844 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1844 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06327352979603935, "min": -0.4349043472953465, "max": 0.2952662448214877, "count": 1844 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.605200052261353, "min": -77.33240008354187, "max": 62.98039984703064, "count": 1844 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06327352979603935, "min": -0.4349043472953465, "max": 0.2952662448214877, "count": 1844 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.605200052261353, "min": -77.33240008354187, "max": 62.98039984703064, "count": 1844 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1844 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1844 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021826821127615404, "min": 0.011657302830280969, "max": 0.02609102944843471, "count": 894 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021826821127615404, "min": 0.011657302830280969, "max": 0.02609102944843471, "count": 894 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08605065693457921, "min": 0.07169382013380528, "max": 0.12169351130723953, "count": 894 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08605065693457921, "min": 0.07169382013380528, "max": 0.12169351130723953, "count": 894 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0873677298426628, "min": 0.07212473005056382, "max": 0.12342467854420344, "count": 894 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0873677298426628, "min": 0.07212473005056382, "max": 0.12342467854420344, "count": 894 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 894 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 894 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 894 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 894 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 894 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 894 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733752631", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/zhangsz/anaconda3/envs/deep_rl_course/bin/mlagents-learn ./SoccerTwos.yaml --env=../ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-debug --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1733779195" }, "total": 26564.170061824, "count": 1, "self": 5.735672844002693, "children": { "run_training.setup": { "total": 0.016341089999997394, "count": 1, "self": 0.016341089999997394 }, "TrainerController.start_learning": { "total": 26558.418047889998, "count": 1, "self": 16.27938580256523, "children": { "TrainerController._reset_env": { "total": 2.4120728419996027, "count": 38, "self": 2.4120728419996027 }, "TrainerController.advance": { "total": 26539.586466513432, "count": 1267380, "self": 14.695409102725534, "children": { "env_step": { "total": 20610.8784505561, "count": 1267380, "self": 13519.42253980608, "children": { "SubprocessEnvManager._take_step": { "total": 7080.059960516522, "count": 1267380, "self": 98.50023091266303, "children": { "TorchPolicy.evaluate": { "total": 6981.559729603859, "count": 2308482, "self": 6981.559729603859 } } }, "workers": { "total": 11.395950233499804, "count": 1267380, "self": 0.0, "children": { "worker_root": { "total": 26523.549686335948, "count": 1267380, "is_parallel": true, "self": 14694.419936251274, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017620039999926007, "count": 2, "is_parallel": true, "self": 0.0007527659999979619, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010092379999946388, "count": 8, "is_parallel": true, "self": 0.0010092379999946388 } } }, "UnityEnvironment.step": { "total": 0.017917139000005022, "count": 1, "is_parallel": true, "self": 0.00029563500001472676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002221390000016754, "count": 1, "is_parallel": true, "self": 0.0002221390000016754 }, "communicator.exchange": { "total": 0.016483568999994702, "count": 1, "is_parallel": true, "self": 0.016483568999994702 }, "steps_from_proto": { "total": 0.000915795999993918, "count": 2, "is_parallel": true, "self": 0.00022799099998849215, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006878050000054259, "count": 8, "is_parallel": true, "self": 0.0006878050000054259 } } } } } } }, "steps_from_proto": { "total": 0.0303977620057978, "count": 74, "is_parallel": true, "self": 0.006590180996589368, "children": { "_process_rank_one_or_two_observation": { "total": 0.023807581009208434, "count": 296, "is_parallel": true, "self": 0.023807581009208434 } } }, "UnityEnvironment.step": { "total": 11829.099352322668, "count": 1267379, "is_parallel": true, "self": 328.7603502342481, "children": { "UnityEnvironment._generate_step_input": { "total": 203.86634577828423, "count": 1267379, "is_parallel": true, "self": 203.86634577828423 }, "communicator.exchange": { "total": 10340.955320573892, "count": 1267379, "is_parallel": true, "self": 10340.955320573892 }, "steps_from_proto": { "total": 955.517335736244, "count": 2534758, "is_parallel": true, "self": 207.19493583769452, "children": { "_process_rank_one_or_two_observation": { "total": 748.3223998985495, "count": 10139032, "is_parallel": true, "self": 748.3223998985495 } } } } } } } } } } }, "trainer_advance": { "total": 5914.012606854603, "count": 1267380, "self": 122.59324357371406, "children": { "process_trajectory": { "total": 3067.5393345179223, "count": 1267380, "self": 3062.31642538492, "children": { "RLTrainer._checkpoint": { "total": 5.222909133002304, "count": 37, "self": 5.222909133002304 } } }, "_update_policy": { "total": 2723.8800287629674, "count": 894, "self": 1398.6412164982567, "children": { "TorchPOCAOptimizer.update": { "total": 1325.2388122647108, "count": 26820, "self": 1325.2388122647108 } } } } } } }, "trainer_threads": { "total": 4.6800050768069923e-07, "count": 1, "self": 4.6800050768069923e-07 }, "TrainerController._save_models": { "total": 0.1401222640015476, "count": 1, "self": 0.0008723770006326959, "children": { "RLTrainer._checkpoint": { "total": 0.1392498870009149, "count": 1, "self": 0.1392498870009149 } } } } } } }