{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1731326580047607, "min": 3.1389458179473877, "max": 3.295710325241089, "count": 151 }, "SoccerTwos.Policy.Entropy.sum": { "value": 70367.390625, "min": 19626.33203125, "max": 123203.125, "count": 151 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 755.6666666666666, "min": 365.93333333333334, "max": 999.0, "count": 151 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18136.0, "min": 16312.0, "max": 23784.0, "count": 151 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.1485471452395, "min": 1188.5563846101525, "max": 1206.812589418782, "count": 122 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4764.594188580958, "min": 2378.909118046842, "max": 21697.057137303003, "count": 122 }, "SoccerTwos.Step.mean": { "value": 1509592.0, "min": 9906.0, "max": 1509592.0, "count": 151 }, "SoccerTwos.Step.sum": { "value": 1509592.0, "min": 9906.0, "max": 1509592.0, "count": 151 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0156563650816679, "min": -0.034405674785375595, "max": 0.009085466153919697, "count": 151 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.20353275537490845, "min": -0.5636743307113647, "max": 0.1015300527215004, "count": 151 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016541888937354088, "min": -0.03664654865860939, "max": 0.00963553600013256, "count": 151 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2150445580482483, "min": -0.6596378684043884, "max": 0.1038656085729599, "count": 151 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 151 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 151 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3076923076923077, "min": -0.5, "max": 0.26288571528026033, "count": 151 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0, "min": -7.635200023651123, "max": 3.680400013923645, "count": 151 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3076923076923077, "min": -0.5, "max": 0.26288571528026033, "count": 151 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0, "min": -7.635200023651123, "max": 3.680400013923645, "count": 151 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 151 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 151 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017732016303731748, "min": 0.009904975417884997, "max": 0.02229291487795611, "count": 70 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017732016303731748, "min": 0.009904975417884997, "max": 0.02229291487795611, "count": 70 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0038435170116523903, "min": 2.265256665244427e-05, "max": 0.0053416890014583865, "count": 70 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0038435170116523903, "min": 2.265256665244427e-05, "max": 0.0053416890014583865, "count": 70 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0038676550922294457, "min": 2.375919448240893e-05, "max": 0.00536214706953615, "count": 70 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0038676550922294457, "min": 2.375919448240893e-05, "max": 0.00536214706953615, "count": 70 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 70 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 70 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 70 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 70 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 70 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 70 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703416239", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\jjate\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1703423745" }, "total": 7506.528188400001, "count": 1, "self": 3.437220600000728, "children": { "run_training.setup": { "total": 0.19520100000045204, "count": 1, "self": 0.19520100000045204 }, "TrainerController.start_learning": { "total": 7502.8957668, "count": 1, "self": 3.173692099890104, "children": { "TrainerController._reset_env": { "total": 10.703865899999073, "count": 8, "self": 10.703865899999073 }, "TrainerController.advance": { "total": 7488.780769900111, "count": 98962, "self": 3.5527895000213903, "children": { "env_step": { "total": 3019.824700299956, "count": 98962, "self": 2367.3585032006704, "children": { "SubprocessEnvManager._take_step": { "total": 650.309711699394, "count": 98962, "self": 23.147655099777694, "children": { "TorchPolicy.evaluate": { "total": 627.1620565996163, "count": 196480, "self": 627.1620565996163 } } }, "workers": { "total": 2.156485399891608, "count": 98961, "self": 0.0, "children": { "worker_root": { "total": 7488.278947000372, "count": 98961, "is_parallel": true, "self": 5578.578590100815, "children": { "steps_from_proto": { "total": 0.019332500000018626, "count": 16, "is_parallel": true, "self": 0.003944000003684778, "children": { "_process_rank_one_or_two_observation": { "total": 0.015388499996333849, "count": 64, "is_parallel": true, "self": 0.015388499996333849 } } }, "UnityEnvironment.step": { "total": 1909.681024399557, "count": 98961, "is_parallel": true, "self": 112.88234799999555, "children": { "UnityEnvironment._generate_step_input": { "total": 105.6323141995199, "count": 98961, "is_parallel": true, "self": 105.6323141995199 }, "communicator.exchange": { "total": 1328.4836378997734, "count": 98961, "is_parallel": true, "self": 1328.4836378997734 }, "steps_from_proto": { "total": 362.6827243002681, "count": 197922, "is_parallel": true, "self": 71.28950160027671, "children": { "_process_rank_one_or_two_observation": { "total": 291.3932226999914, "count": 791688, "is_parallel": true, "self": 291.3932226999914 } } } } } } } } } } }, "trainer_advance": { "total": 4465.403280100134, "count": 98961, "self": 23.74667270025202, "children": { "process_trajectory": { "total": 937.7399391998752, "count": 98961, "self": 937.0562744998733, "children": { "RLTrainer._checkpoint": { "total": 0.6836647000018274, "count": 3, "self": 0.6836647000018274 } } }, "_update_policy": { "total": 3503.916668200007, "count": 70, "self": 328.96328920007363, "children": { "TorchPOCAOptimizer.update": { "total": 3174.953378999933, "count": 2103, "self": 3174.953378999933 } } } } } } }, "trainer_threads": { "total": 2.5999979698099196e-06, "count": 1, "self": 2.5999979698099196e-06 }, "TrainerController._save_models": { "total": 0.23743630000171834, "count": 1, "self": 0.01348350000262144, "children": { "RLTrainer._checkpoint": { "total": 0.2239527999990969, "count": 1, "self": 0.2239527999990969 } } } } } } }