| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.1996026039123535, | |
| "min": 2.9278101921081543, | |
| "max": 3.2722084522247314, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 62328.2578125, | |
| "min": 49968.30078125, | |
| "max": 74948.84375, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 810.6666666666666, | |
| "min": 531.6666666666666, | |
| "max": 999.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19456.0, | |
| "min": 16516.0, | |
| "max": 23324.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1204.0218902996917, | |
| "min": 1199.5028730369677, | |
| "max": 1210.6164886930674, | |
| "count": 69 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 4816.087561198767, | |
| "min": 2400.4997554563024, | |
| "max": 14461.67778818551, | |
| "count": 69 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 1019052.0, | |
| "min": 9478.0, | |
| "max": 1019052.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 1019052.0, | |
| "min": 9478.0, | |
| "max": 1019052.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.020359380170702934, | |
| "min": -0.03247058019042015, | |
| "max": 0.0642065554857254, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 0.24431255459785461, | |
| "min": -0.42885616421699524, | |
| "max": 0.8988363742828369, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.018934523686766624, | |
| "min": -0.044129129499197006, | |
| "max": 0.06423702090978622, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 0.2272142916917801, | |
| "min": -0.48542043566703796, | |
| "max": 0.8992221355438232, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.14220000058412552, | |
| "min": -0.5333333333333333, | |
| "max": 0.3313599983851115, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -1.7064000070095062, | |
| "min": -8.0, | |
| "max": 5.485599935054779, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.14220000058412552, | |
| "min": -0.5333333333333333, | |
| "max": 0.3313599983851115, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -1.7064000070095062, | |
| "min": -8.0, | |
| "max": 5.485599935054779, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 102 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.017422009384851358, | |
| "min": 0.013289852785722664, | |
| "max": 0.021624805549314865, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.017422009384851358, | |
| "min": 0.013289852785722664, | |
| "max": 0.021624805549314865, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0021655489845822254, | |
| "min": 2.518433211662341e-06, | |
| "max": 0.006047092261724174, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0021655489845822254, | |
| "min": 2.518433211662341e-06, | |
| "max": 0.006047092261724174, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.002190248357752959, | |
| "min": 3.3172456975686753e-06, | |
| "max": 0.00505002357531339, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.002190248357752959, | |
| "min": 3.3172456975686753e-06, | |
| "max": 0.00505002357531339, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 47 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 47 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1673807868", | |
| "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/linux-x86_64/soccer-twos/soccer-twos --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "0.29.0.dev0", | |
| "mlagents_envs_version": "0.29.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.8.1+cu102", | |
| "numpy_version": "1.21.6", | |
| "end_time_seconds": "1673814156" | |
| }, | |
| "total": 6287.747221217, | |
| "count": 1, | |
| "self": 10.005318574998455, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.1071236590000808, | |
| "count": 1, | |
| "self": 0.1071236590000808 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 6277.634778983001, | |
| "count": 1, | |
| "self": 9.346853454097982, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 6.287176204000843, | |
| "count": 6, | |
| "self": 6.287176204000843 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 6261.662972145901, | |
| "count": 514320, | |
| "self": 9.436193643903607, | |
| "children": { | |
| "env_step": { | |
| "total": 5814.310632615159, | |
| "count": 514320, | |
| "self": 3150.765826409681, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 2657.5126975569865, | |
| "count": 514320, | |
| "self": 64.71362542510724, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 2592.7990721318793, | |
| "count": 1027698, | |
| "self": 521.0321252985041, | |
| "children": { | |
| "TorchPolicy.sample_actions": { | |
| "total": 2071.766946833375, | |
| "count": 1027698, | |
| "self": 2071.766946833375 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 6.032108648491885, | |
| "count": 514319, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 6249.836879560299, | |
| "count": 514319, | |
| "is_parallel": true, | |
| "self": 3779.7106470330614, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0017015900000387774, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.000768551000419393, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0009330389996193844, | |
| "count": 12, | |
| "is_parallel": true, | |
| "self": 0.0009330389996193844 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.026431305999949473, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003021919997081568, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0002521020001040597, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002521020001040597 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.0243987260000722, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0243987260000722 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0014782860000650544, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006566069998825697, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0008216790001824847, | |
| "count": 12, | |
| "is_parallel": true, | |
| "self": 0.0008216790001824847 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 2470.121857965237, | |
| "count": 514318, | |
| "is_parallel": true, | |
| "self": 122.82167207231305, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 81.66833717314012, | |
| "count": 514318, | |
| "is_parallel": true, | |
| "self": 81.66833717314012 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1582.744087071872, | |
| "count": 514318, | |
| "is_parallel": true, | |
| "self": 1582.744087071872 | |
| }, | |
| "steps_from_proto": { | |
| "total": 682.8877616479117, | |
| "count": 1028636, | |
| "is_parallel": true, | |
| "self": 295.6551202482824, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 387.2326413996293, | |
| "count": 6171816, | |
| "is_parallel": true, | |
| "self": 387.2326413996293 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.004374562000975857, | |
| "count": 10, | |
| "is_parallel": true, | |
| "self": 0.0019437449996075884, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0024308170013682684, | |
| "count": 60, | |
| "is_parallel": true, | |
| "self": 0.0024308170013682684 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 437.9161458868384, | |
| "count": 514319, | |
| "self": 27.845883952824124, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 119.94541229301785, | |
| "count": 514319, | |
| "self": 119.49111925601801, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.454293036999843, | |
| "count": 2, | |
| "self": 0.454293036999843 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 290.12484964099644, | |
| "count": 47, | |
| "self": 180.0239040919996, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 110.10094554899683, | |
| "count": 1410, | |
| "self": 110.10094554899683 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.3760000001639128e-06, | |
| "count": 1, | |
| "self": 1.3760000001639128e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.33777580300011323, | |
| "count": 1, | |
| "self": 0.0021911399999225978, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.33558466300019063, | |
| "count": 1, | |
| "self": 0.33558466300019063 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |