{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0496420860290527, "min": 1.9699488878250122, "max": 3.2957611083984375, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40140.19140625, "min": 24006.47265625, "max": 114063.3125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.9054054054054, "min": 44.41284403669725, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19212.0, "min": 13220.0, "max": 29168.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1508.2401412097033, "min": 1197.2503267915763, "max": 1531.330232998366, "count": 493 }, "SoccerTwos.Self-play.ELO.sum": { "value": 223219.5408990361, "min": 2394.5006535831526, "max": 319620.43788398313, "count": 493 }, "SoccerTwos.Step.mean": { "value": 4999923.0, "min": 9600.0, "max": 4999923.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999923.0, "min": 9600.0, "max": 4999923.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.049563899636268616, "min": -0.11589053273200989, "max": 0.15836215019226074, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.385021209716797, "min": -17.47100067138672, "max": 24.229408264160156, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04883383587002754, "min": -0.11587277054786682, "max": 0.1570761501789093, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.276241302490234, "min": -16.950939178466797, "max": 24.032649993896484, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.052849665184149006, "min": -0.6153846153846154, "max": 0.5347857155970165, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.874600112438202, "min": -45.040000200271606, "max": 43.72359982132912, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.052849665184149006, "min": -0.6153846153846154, "max": 0.5347857155970165, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.874600112438202, "min": -45.040000200271606, "max": 43.72359982132912, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016398119295869644, "min": 0.011055969167500734, "max": 0.024588115167959283, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016398119295869644, "min": 0.011055969167500734, "max": 0.024588115167959283, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08516770402590433, "min": 7.862386361618216e-05, "max": 0.10642808551589648, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08516770402590433, "min": 7.862386361618216e-05, "max": 0.10642808551589648, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08607020055254301, "min": 7.850312686059624e-05, "max": 0.1089834230641524, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08607020055254301, "min": 7.850312686059624e-05, "max": 0.1089834230641524, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705676443", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/weixia/anaconda3/envs/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --run-id=SoccerTwos --no-graphics --env=./training-envs-executables/SoccerTwos/SoccerTwos", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2", "numpy_version": "1.23.5", "end_time_seconds": "1705715930" }, "total": 39486.13023382297, "count": 1, "self": 0.36589545098831877, "children": { "run_training.setup": { "total": 0.3835012780036777, "count": 1, "self": 0.3835012780036777 }, "TrainerController.start_learning": { "total": 39485.38083709398, "count": 1, "self": 8.156851188279688, "children": { "TrainerController._reset_env": { "total": 9.28777388803428, "count": 25, "self": 9.28777388803428 }, "TrainerController.advance": { "total": 39467.70460541861, "count": 339528, "self": 8.637577339017298, "children": { "env_step": { "total": 31376.298405682144, "count": 339528, "self": 30311.752292448247, "children": { "SubprocessEnvManager._take_step": { "total": 1059.2864602305926, "count": 339528, "self": 47.3477015644894, "children": { "TorchPolicy.evaluate": { "total": 1011.9387586661032, "count": 632088, "self": 1011.9387586661032 } } }, "workers": { "total": 5.259653003304265, "count": 339528, "self": 0.0, "children": { "worker_root": { "total": 39463.83894943661, "count": 339528, "is_parallel": true, "self": 10071.512773024151, "children": { "steps_from_proto": { "total": 0.06006579514360055, "count": 50, "is_parallel": true, "self": 0.010921472101472318, "children": { "_process_rank_one_or_two_observation": { "total": 0.049144323042128235, "count": 200, "is_parallel": true, "self": 0.049144323042128235 } } }, "UnityEnvironment.step": { "total": 29392.26611061732, "count": 339528, "is_parallel": true, "self": 101.78308359050425, "children": { "UnityEnvironment._generate_step_input": { "total": 517.6364895065199, "count": 339528, "is_parallel": true, "self": 517.6364895065199 }, "communicator.exchange": { "total": 27940.528813199024, "count": 339528, "is_parallel": true, "self": 27940.528813199024 }, "steps_from_proto": { "total": 832.3177243212704, "count": 679056, "is_parallel": true, "self": 151.60361823969288, "children": { "_process_rank_one_or_two_observation": { "total": 680.7141060815775, "count": 2716224, "is_parallel": true, "self": 680.7141060815775 } } } } } } } } } } }, "trainer_advance": { "total": 8082.768622397445, "count": 339528, "self": 60.456031884707045, "children": { "process_trajectory": { "total": 1090.7197146839462, "count": 339528, "self": 1088.320764566015, "children": { "RLTrainer._checkpoint": { "total": 2.3989501179312356, "count": 10, "self": 2.3989501179312356 } } }, "_update_policy": { "total": 6931.592875828792, "count": 240, "self": 712.5933588306652, "children": { "TorchPOCAOptimizer.update": { "total": 6218.999516998127, "count": 7200, "self": 6218.999516998127 } } } } } } }, "trainer_threads": { "total": 9.860377758741379e-07, "count": 1, "self": 9.860377758741379e-07 }, "TrainerController._save_models": { "total": 0.23160561302211136, "count": 1, "self": 0.0013614699710160494, "children": { "RLTrainer._checkpoint": { "total": 0.2302441430510953, "count": 1, "self": 0.2302441430510953 } } } } } } }