{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3972941637039185, "min": 1.285732626914978, "max": 3.2957520484924316, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27319.89453125, "min": 22465.439453125, "max": 105464.0625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 86.96428571428571, "min": 41.85470085470085, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19480.0, "min": 12948.0, "max": 30384.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1656.5532181521019, "min": 1192.0640787340647, "max": 1761.2894049839942, "count": 4984 }, "SoccerTwos.Self-play.ELO.sum": { "value": 185533.96043303542, "min": 2387.000884273693, "max": 390578.5637410532, "count": 4984 }, "SoccerTwos.Step.mean": { "value": 49999914.0, "min": 9208.0, "max": 49999914.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999914.0, "min": 9208.0, "max": 49999914.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03263528645038605, "min": -0.12490427494049072, "max": 0.1818830519914627, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.6877875328063965, "min": -22.885658264160156, "max": 35.649078369140625, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03411535918712616, "min": -0.12752260267734528, "max": 0.1826234608888626, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.8550355434417725, "min": -22.78534507751465, "max": 35.79419708251953, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.05500884815654923, "min": -0.828371429017612, "max": 0.5015090974894437, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.2159998416900635, "min": -71.7260000705719, "max": 77.86560010910034, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05500884815654923, "min": -0.828371429017612, "max": 0.5015090974894437, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.2159998416900635, "min": -71.7260000705719, "max": 77.86560010910034, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02252829516849791, "min": 0.010176922385532331, "max": 0.02608171648074252, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02252829516849791, "min": 0.010176922385532331, "max": 0.02608171648074252, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0808956374724706, "min": 4.394343166798838e-06, "max": 0.1212976984679699, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0808956374724706, "min": 4.394343166798838e-06, "max": 0.1212976984679699, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08190159449974696, "min": 4.7147190495403874e-06, "max": 0.12247925847768784, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08190159449974696, "min": 4.7147190495403874e-06, "max": 0.12247925847768784, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708532550", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/data/home/adityacv/anaconda3/envs/mla/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708602499" }, "total": 69949.030304702, "count": 1, "self": 0.4681981570320204, "children": { "run_training.setup": { "total": 0.01178661291487515, "count": 1, "self": 0.01178661291487515 }, "TrainerController.start_learning": { "total": 69948.55031993205, "count": 1, "self": 31.1824635991361, "children": { "TrainerController._reset_env": { "total": 4.883301006979309, "count": 250, "self": 4.883301006979309 }, "TrainerController.advance": { "total": 69912.13297457201, "count": 3431941, "self": 34.62998353119474, "children": { "env_step": { "total": 56880.90749909496, "count": 3431941, "self": 38933.40851271374, "children": { "SubprocessEnvManager._take_step": { "total": 17928.185198108084, "count": 3431941, "self": 240.953698049183, "children": { "TorchPolicy.evaluate": { "total": 17687.2315000589, "count": 6279836, "self": 17687.2315000589 } } }, "workers": { "total": 19.313788273138925, "count": 3431941, "self": 0.0, "children": { "worker_root": { "total": 69895.10759405745, "count": 3431941, "is_parallel": true, "self": 35278.502755678375, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002374101895838976, "count": 2, "is_parallel": true, "self": 0.0005878220545127988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017862798413261771, "count": 8, "is_parallel": true, "self": 0.0017862798413261771 } } }, "UnityEnvironment.step": { "total": 0.015894436975941062, "count": 1, "is_parallel": true, "self": 0.0004038279876112938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033038004767149687, "count": 1, "is_parallel": true, "self": 0.00033038004767149687 }, "communicator.exchange": { "total": 0.013942104997113347, "count": 1, "is_parallel": true, "self": 0.013942104997113347 }, "steps_from_proto": { "total": 0.0012181239435449243, "count": 2, "is_parallel": true, "self": 0.00023312412668019533, "children": { "_process_rank_one_or_two_observation": { "total": 0.000984999816864729, "count": 8, "is_parallel": true, "self": 0.000984999816864729 } } } } } } }, "UnityEnvironment.step": { "total": 34616.06519816734, "count": 3431940, "is_parallel": true, "self": 1272.0759775217157, "children": { "UnityEnvironment._generate_step_input": { "total": 818.3795400334056, "count": 3431940, "is_parallel": true, "self": 818.3795400334056 }, "communicator.exchange": { "total": 28709.032677426352, "count": 3431940, "is_parallel": true, "self": 28709.032677426352 }, "steps_from_proto": { "total": 3816.57700318587, "count": 6863880, "is_parallel": true, "self": 683.8799885136541, "children": { "_process_rank_one_or_two_observation": { "total": 3132.697014672216, "count": 27455520, "is_parallel": true, "self": 3132.697014672216 } } } } }, "steps_from_proto": { "total": 0.5396402117330581, "count": 498, "is_parallel": true, "self": 0.0967952188802883, "children": { "_process_rank_one_or_two_observation": { "total": 0.4428449928527698, "count": 1992, "is_parallel": true, "self": 0.4428449928527698 } } } } } } } } }, "trainer_advance": { "total": 12996.59549194586, "count": 3431941, "self": 278.6270368200494, "children": { "process_trajectory": { "total": 6458.452643502853, "count": 3431941, "self": 6427.417760323384, "children": { "RLTrainer._checkpoint": { "total": 31.034883179469034, "count": 100, "self": 31.034883179469034 } } }, "_update_policy": { "total": 6259.515811622958, "count": 2424, "self": 3791.8440035417443, "children": { "TorchPOCAOptimizer.update": { "total": 2467.6718080812134, "count": 72720, "self": 2467.6718080812134 } } } } } } }, "trainer_threads": { "total": 6.019836291670799e-07, "count": 1, "self": 6.019836291670799e-07 }, "TrainerController._save_models": { "total": 0.3515801519388333, "count": 1, "self": 0.001964784925803542, "children": { "RLTrainer._checkpoint": { "total": 0.34961536701302975, "count": 1, "self": 0.34961536701302975 } } } } } } }