{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.1660494804382324, "min": 1.163506269454956, "max": 1.5379496812820435, "count": 295 }, "SoccerTwos.Policy.Entropy.sum": { "value": 23582.18359375, "min": 19643.19921875, "max": 35234.51953125, "count": 295 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.03409090909091, "min": 51.357894736842105, "max": 114.25, "count": 295 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 18504.0, "max": 20940.0, "count": 295 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1765.943921066491, "min": 1677.620447333749, "max": 1765.943921066491, "count": 295 }, "SoccerTwos.Self-play.ELO.sum": { "value": 310806.1301077024, "min": 151670.54174021896, "max": 327663.5806721868, "count": 295 }, "SoccerTwos.Step.mean": { "value": 34999970.0, "min": 32059955.0, "max": 34999970.0, "count": 295 }, "SoccerTwos.Step.sum": { "value": 34999970.0, "min": 32059955.0, "max": 34999970.0, "count": 295 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.001140120322816074, "min": -0.10083454847335815, "max": 0.042552459985017776, "count": 295 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.19952106475830078, "min": -14.988079071044922, "max": 5.947393894195557, "count": 295 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0022361918818205595, "min": -0.09997288882732391, "max": 0.04147672653198242, "count": 295 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.39133358001708984, "min": -15.114870071411133, "max": 5.880364894866943, "count": 295 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 295 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 295 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.046221715382167274, "min": -0.3833907290010263, "max": 0.2875151093915212, "count": 295 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.088800191879272, "min": -57.89200007915497, "max": 39.96460020542145, "count": 295 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.046221715382167274, "min": -0.3833907290010263, "max": 0.2875151093915212, "count": 295 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.088800191879272, "min": -57.89200007915497, "max": 39.96460020542145, "count": 295 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 295 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 295 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01998710645517955, "min": 0.013047904896181232, "max": 0.022752037628864248, "count": 143 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01998710645517955, "min": 0.013047904896181232, "max": 0.022752037628864248, "count": 143 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09735343083739281, "min": 0.07494692032535871, "max": 0.10981472209095955, "count": 143 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09735343083739281, "min": 0.07494692032535871, "max": 0.10981472209095955, "count": 143 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09839346880714099, "min": 0.07544731299082438, "max": 0.11057015061378479, "count": 143 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09839346880714099, "min": 0.07544731299082438, "max": 0.11057015061378479, "count": 143 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 143 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 143 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 143 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 143 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.003000000000000001, "min": 0.003000000000000001, "max": 0.003000000000000001, "count": 143 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.003000000000000001, "min": 0.003000000000000001, "max": 0.003000000000000001, "count": 143 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714002747", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/luyijie/anaconda3/envs/rl/bin/mlagents-learn ./config/SoccerTwos/poca_3_layer_15M.yaml --env=../test_env/SoccerTwos.x86_64 --run-id=poca_3_layer_run2 --resume --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714006276" }, "total": 3528.3960621570004, "count": 1, "self": 0.21940860597533174, "children": { "run_training.setup": { "total": 0.019762242009164765, "count": 1, "self": 0.019762242009164765 }, "TrainerController.start_learning": { "total": 3528.156891309016, "count": 1, "self": 2.8068258461134974, "children": { "TrainerController._reset_env": { "total": 1.0686781560070813, "count": 16, "self": 1.0686781560070813 }, "TrainerController.advance": { "total": 3524.159241624875, "count": 201816, "self": 2.9596669372403994, "children": { "env_step": { "total": 2688.116283382813, "count": 201816, "self": 2147.7309492602944, "children": { "SubprocessEnvManager._take_step": { "total": 538.3741281694965, "count": 201816, "self": 19.001167727459688, "children": { "TorchPolicy.evaluate": { "total": 519.3729604420369, "count": 370430, "self": 519.3729604420369 } } }, "workers": { "total": 2.0112059530219994, "count": 201816, "self": 0.0, "children": { "worker_root": { "total": 3523.7675522350182, "count": 201816, "is_parallel": true, "self": 1722.7399015523551, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015797200030647218, "count": 2, "is_parallel": true, "self": 0.00037731899647042155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012024010065943003, "count": 8, "is_parallel": true, "self": 0.0012024010065943003 } } }, "UnityEnvironment.step": { "total": 0.0223209060204681, "count": 1, "is_parallel": true, "self": 0.00048822598182596266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002748020051512867, "count": 1, "is_parallel": true, "self": 0.0002748020051512867 }, "communicator.exchange": { "total": 0.020063389994902536, "count": 1, "is_parallel": true, "self": 0.020063389994902536 }, "steps_from_proto": { "total": 0.0014944880385883152, "count": 2, "is_parallel": true, "self": 0.00026823501684702933, "children": { "_process_rank_one_or_two_observation": { "total": 0.001226253021741286, "count": 8, "is_parallel": true, "self": 0.001226253021741286 } } } } } } }, "steps_from_proto": { "total": 0.016255242080660537, "count": 30, "is_parallel": true, "self": 0.0031940351182129234, "children": { "_process_rank_one_or_two_observation": { "total": 0.013061206962447613, "count": 120, "is_parallel": true, "self": 0.013061206962447613 } } }, "UnityEnvironment.step": { "total": 1801.0113954405824, "count": 201815, "is_parallel": true, "self": 86.53916094452143, "children": { "UnityEnvironment._generate_step_input": { "total": 47.5667131379887, "count": 201815, "is_parallel": true, "self": 47.5667131379887 }, "communicator.exchange": { "total": 1435.8657774784951, "count": 201815, "is_parallel": true, "self": 1435.8657774784951 }, "steps_from_proto": { "total": 231.03974387957714, "count": 403630, "is_parallel": true, "self": 44.62914385346812, "children": { "_process_rank_one_or_two_observation": { "total": 186.41060002610902, "count": 1614520, "is_parallel": true, "self": 186.41060002610902 } } } } } } } } } } }, "trainer_advance": { "total": 833.0832913048216, "count": 201816, "self": 21.082576109969523, "children": { "process_trajectory": { "total": 280.2782274468045, "count": 201816, "self": 279.4932862937858, "children": { "RLTrainer._checkpoint": { "total": 0.7849411530187353, "count": 6, "self": 0.7849411530187353 } } }, "_update_policy": { "total": 531.7224877480476, "count": 143, "self": 212.42356030928204, "children": { "TorchPOCAOptimizer.update": { "total": 319.29892743876553, "count": 4290, "self": 319.29892743876553 } } } } } } }, "trainer_threads": { "total": 5.00003807246685e-07, "count": 1, "self": 5.00003807246685e-07 }, "TrainerController._save_models": { "total": 0.12214518201653846, "count": 1, "self": 0.00182851601857692, "children": { "RLTrainer._checkpoint": { "total": 0.12031666599796154, "count": 1, "self": 0.12031666599796154 } } } } } } }