{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2478506565093994, "min": 2.2357864379882812, "max": 2.4217634201049805, "count": 67 }, "SoccerTwos.Policy.Entropy.sum": { "value": 91064.921875, "min": 38863.625, "max": 101055.34375, "count": 67 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 42.06086956521739, "min": 40.87777777777778, "max": 53.73770491803279, "count": 67 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 38696.0, "min": 14716.0, "max": 39844.0, "count": 67 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.0246153318647, "min": 1176.5456932491104, "max": 1227.0267909219529, "count": 67 }, "SoccerTwos.Self-play.ELO.sum": { "value": 550631.3230526578, "min": 213921.57633360883, "max": 572177.7661286313, "count": 67 }, "SoccerTwos.Step.mean": { "value": 6879981.0, "min": 5559962.0, "max": 6879981.0, "count": 67 }, "SoccerTwos.Step.sum": { "value": 6879981.0, "min": 5559962.0, "max": 6879981.0, "count": 67 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.018729526549577713, "min": -0.041034113615751266, "max": 0.053876958787441254, "count": 67 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.615582466125488, "min": -17.23432731628418, "max": 22.52056884765625, "count": 67 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01690117083489895, "min": -0.04584740102291107, "max": 0.0544377937912941, "count": 67 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.774538993835449, "min": -19.255908966064453, "max": 22.75499725341797, "count": 67 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 67 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 67 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.029700001426365065, "min": -0.16277437106422757, "max": 0.1755102143718058, "count": 67 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.66200065612793, "min": -71.13240015506744, "max": 73.88980025053024, "count": 67 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.029700001426365065, "min": -0.16277437106422757, "max": 0.1755102143718058, "count": 67 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.66200065612793, "min": -71.13240015506744, "max": 73.88980025053024, "count": 67 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018331647620863804, "min": 0.01613544496940449, "max": 0.01887765062280232, "count": 12 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018331647620863804, "min": 0.01613544496940449, "max": 0.01887765062280232, "count": 12 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06169401177763939, "min": 0.05694894982874393, "max": 0.06169401177763939, "count": 12 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06169401177763939, "min": 0.05694894982874393, "max": 0.06169401177763939, "count": 12 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06926548351347446, "min": 0.0646216332167387, "max": 0.06926548351347446, "count": 12 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06926548351347446, "min": 0.0646216332167387, "max": 0.06926548351347446, "count": 12 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00016086901782621, "min": 0.00016086901782621, "max": 0.00021725030654994994, "count": 12 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00016086901782621, "min": 0.00016086901782621, "max": 0.00021725030654994994, "count": 12 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.13217378999999996, "min": 0.13217378999999996, "max": 0.14345004999999997, "count": 12 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.13217378999999996, "min": 0.13217378999999996, "max": 0.14345004999999997, "count": 12 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0016154721210000003, "min": 0.0016154721210000003, "max": 0.0021781574949999998, "count": 12 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0016154721210000003, "min": 0.0016154721210000003, "max": 0.0021781574949999998, "count": 12 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733230749", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/mango/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1733240280" }, "total": 9530.95424354, "count": 1, "self": 1.4487167999977828, "children": { "run_training.setup": { "total": 0.04115357099999528, "count": 1, "self": 0.04115357099999528 }, "TrainerController.start_learning": { "total": 9529.464373169001, "count": 1, "self": 2.0527336289014784, "children": { "TrainerController._reset_env": { "total": 4.559869480998714, "count": 6, "self": 4.559869480998714 }, "TrainerController.advance": { "total": 9522.7014330811, "count": 94878, "self": 1.9191404055654857, "children": { "env_step": { "total": 7025.0258754607985, "count": 94878, "self": 6790.529097738346, "children": { "SubprocessEnvManager._take_step": { "total": 233.28466942114665, "count": 94878, "self": 9.769179835016075, "children": { "TorchPolicy.evaluate": { "total": 223.51548958613057, "count": 167620, "self": 223.51548958613057 } } }, "workers": { "total": 1.2121083013062162, "count": 94877, "self": 0.0, "children": { "worker_root": { "total": 9522.64279122905, "count": 94877, "is_parallel": true, "self": 2940.848590467828, "children": { "steps_from_proto": { "total": 0.016203271999074786, "count": 12, "is_parallel": true, "self": 0.0022021899931132793, "children": { "_process_rank_one_or_two_observation": { "total": 0.014001082005961507, "count": 48, "is_parallel": true, "self": 0.014001082005961507 } } }, "UnityEnvironment.step": { "total": 6581.777997489222, "count": 94877, "is_parallel": true, "self": 21.93422803523572, "children": { "UnityEnvironment._generate_step_input": { "total": 134.36988261496208, "count": 94877, "is_parallel": true, "self": 134.36988261496208 }, "communicator.exchange": { "total": 6176.115223347013, "count": 94877, "is_parallel": true, "self": 6176.115223347013 }, "steps_from_proto": { "total": 249.35866349201115, "count": 189754, "is_parallel": true, "self": 33.914368653379825, "children": { "_process_rank_one_or_two_observation": { "total": 215.44429483863132, "count": 759016, "is_parallel": true, "self": 215.44429483863132 } } } } } } } } } } }, "trainer_advance": { "total": 2495.756417214736, "count": 94877, "self": 12.74757487437364, "children": { "process_trajectory": { "total": 276.40217168436266, "count": 94877, "self": 276.0842088503623, "children": { "RLTrainer._checkpoint": { "total": 0.31796283400035463, "count": 2, "self": 0.31796283400035463 } } }, "_update_policy": { "total": 2206.6066706559996, "count": 13, "self": 303.31123607103837, "children": { "TorchPOCAOptimizer.update": { "total": 1903.2954345849612, "count": 3250, "self": 1903.2954345849612 } } } } } } }, "trainer_threads": { "total": 1.3030003174208105e-06, "count": 1, "self": 1.3030003174208105e-06 }, "TrainerController._save_models": { "total": 0.15033567499995115, "count": 1, "self": 0.0011441690003266558, "children": { "RLTrainer._checkpoint": { "total": 0.1491915059996245, "count": 1, "self": 0.1491915059996245 } } } } } } }