{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1851346492767334, "min": 3.1851346492767334, "max": 3.2957520484924316, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 67168.1171875, "min": 17046.7578125, "max": 110996.2734375, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 940.6, "min": 468.5, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18812.0, "min": 10460.0, "max": 26888.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.1296427442737, "min": 1193.2241495035437, "max": 1207.1645937612016, "count": 46 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2408.2592854885474, "min": 2386.4972693142518, "max": 19314.633500179225, "count": 46 }, "SoccerTwos.Step.mean": { "value": 499136.0, "min": 9924.0, "max": 499136.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499136.0, "min": 9924.0, "max": 499136.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.005582389887422323, "min": -0.010162914171814919, "max": 0.029268814250826836, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.05582389980554581, "min": -0.12195497006177902, "max": 0.43899405002593994, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0063251713290810585, "min": -0.01165727712213993, "max": 0.029276151210069656, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.06325171142816544, "min": -0.13864044845104218, "max": 0.5531743168830872, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2, "min": -0.64546666542689, "max": 0.33782500214874744, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -8.0, "max": 5.405200034379959, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2, "min": -0.64546666542689, "max": 0.33782500214874744, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -8.0, "max": 5.405200034379959, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016768443631008267, "min": 0.011616622659251638, "max": 0.020136999327223747, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016768443631008267, "min": 0.011616622659251638, "max": 0.020136999327223747, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.006825882894918323, "min": 0.0005774281113796557, "max": 0.006825882894918323, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.006825882894918323, "min": 0.0005774281113796557, "max": 0.006825882894918323, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.006874483699599902, "min": 0.0005837453024772306, "max": 0.006874483699599902, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.006874483699599902, "min": 0.0005837453024772306, "max": 0.006874483699599902, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686357514", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/home/ubuntu/miniconda3/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1686358343" }, "total": 828.6380972009993, "count": 1, "self": 0.26953503000004275, "children": { "run_training.setup": { "total": 0.009080740999706904, "count": 1, "self": 0.009080740999706904 }, "TrainerController.start_learning": { "total": 828.3594814299995, "count": 1, "self": 0.5730416862352286, "children": { "TrainerController._reset_env": { "total": 4.000813525997728, "count": 2, "self": 4.000813525997728 }, "TrainerController.advance": { "total": 823.5585414147681, "count": 32388, "self": 0.5957359098156303, "children": { "env_step": { "total": 680.0047385937341, "count": 32388, "self": 503.0328245717137, "children": { "SubprocessEnvManager._take_step": { "total": 176.5783173421769, "count": 32388, "self": 3.2973856529406476, "children": { "TorchPolicy.evaluate": { "total": 173.28093168923624, "count": 64256, "self": 173.28093168923624 } } }, "workers": { "total": 0.3935966798435402, "count": 32388, "self": 0.0, "children": { "worker_root": { "total": 826.8014418639614, "count": 32388, "is_parallel": true, "self": 395.77548004998425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023723929989500903, "count": 2, "is_parallel": true, "self": 0.00046837100126140285, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019040219976886874, "count": 8, "is_parallel": true, "self": 0.0019040219976886874 } } }, "UnityEnvironment.step": { "total": 0.02564005000022007, "count": 1, "is_parallel": true, "self": 0.000626795999778551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005567049993260298, "count": 1, "is_parallel": true, "self": 0.0005567049993260298 }, "communicator.exchange": { "total": 0.022409504001188907, "count": 1, "is_parallel": true, "self": 0.022409504001188907 }, "steps_from_proto": { "total": 0.002047044999926584, "count": 2, "is_parallel": true, "self": 0.00032151899722521193, "children": { "_process_rank_one_or_two_observation": { "total": 0.001725526002701372, "count": 8, "is_parallel": true, "self": 0.001725526002701372 } } } } } } }, "UnityEnvironment.step": { "total": 431.024047273977, "count": 32387, "is_parallel": true, "self": 19.812529582914067, "children": { "UnityEnvironment._generate_step_input": { "total": 14.534202267006549, "count": 32387, "is_parallel": true, "self": 14.534202267006549 }, "communicator.exchange": { "total": 335.34142193796833, "count": 32387, "is_parallel": true, "self": 335.34142193796833 }, "steps_from_proto": { "total": 61.335893486088025, "count": 64774, "is_parallel": true, "self": 8.832665478112176, "children": { "_process_rank_one_or_two_observation": { "total": 52.50322800797585, "count": 259096, "is_parallel": true, "self": 52.50322800797585 } } } } }, "steps_from_proto": { "total": 0.001914540000143461, "count": 2, "is_parallel": true, "self": 0.00028034599745296873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016341940026904922, "count": 8, "is_parallel": true, "self": 0.0016341940026904922 } } } } } } } } }, "trainer_advance": { "total": 142.95806691121834, "count": 32388, "self": 5.27200267445005, "children": { "process_trajectory": { "total": 36.33480955577397, "count": 32388, "self": 36.15106283277419, "children": { "RLTrainer._checkpoint": { "total": 0.18374672299978556, "count": 1, "self": 0.18374672299978556 } } }, "_update_policy": { "total": 101.35125468099432, "count": 22, "self": 71.84356611401017, "children": { "TorchPOCAOptimizer.update": { "total": 29.507688566984143, "count": 666, "self": 29.507688566984143 } } } } } } }, "trainer_threads": { "total": 8.009992598090321e-07, "count": 1, "self": 8.009992598090321e-07 }, "TrainerController._save_models": { "total": 0.22708400199917378, "count": 1, "self": 0.0013322239992703544, "children": { "RLTrainer._checkpoint": { "total": 0.22575177799990342, "count": 1, "self": 0.22575177799990342 } } } } } } }