{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.886430263519287, "min": 2.806196928024292, "max": 3.2956626415252686, "count": 124 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57636.23828125, "min": 14634.5126953125, "max": 109185.234375, "count": 124 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 86.41071428571429, "min": 79.98412698412699, "max": 999.0, "count": 124 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19356.0, "min": 8380.0, "max": 27000.0, "count": 124 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1345.4823567514406, "min": 1198.9970947669865, "max": 1345.4823567514406, "count": 121 }, "SoccerTwos.Self-play.ELO.sum": { "value": 150694.02395616134, "min": 2397.9941895339734, "max": 168202.87468894984, "count": 121 }, "SoccerTwos.Step.mean": { "value": 1239923.0, "min": 9196.0, "max": 1239923.0, "count": 124 }, "SoccerTwos.Step.sum": { "value": 1239923.0, "min": 9196.0, "max": 1239923.0, "count": 124 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.11026978492736816, "min": -0.08389207720756531, "max": 0.16095934808254242, "count": 124 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 12.460485458374023, "min": -1.0905958414077759, "max": 15.958245277404785, "count": 124 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.11049355566501617, "min": -0.08388417214155197, "max": 0.16049960255622864, "count": 124 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 12.485772132873535, "min": -1.0904635190963745, "max": 15.856868743896484, "count": 124 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 124 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 124 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.32790796419160556, "min": -0.6259076916254483, "max": 0.4461333420541551, "count": 124 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 37.05359995365143, "min": -27.90720009803772, "max": 37.05359995365143, "count": 124 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.32790796419160556, "min": -0.6259076916254483, "max": 0.4461333420541551, "count": 124 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 37.05359995365143, "min": -27.90720009803772, "max": 37.05359995365143, "count": 124 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 124 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 124 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017933064362053604, "min": 0.010807520801123852, "max": 0.02106685910645562, "count": 58 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017933064362053604, "min": 0.010807520801123852, "max": 0.02106685910645562, "count": 58 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.059848784531156225, "min": 0.0005380973469679399, "max": 0.059848784531156225, "count": 58 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.059848784531156225, "min": 0.0005380973469679399, "max": 0.059848784531156225, "count": 58 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0615954947968324, "min": 0.0005495274681986, "max": 0.0615954947968324, "count": 58 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0615954947968324, "min": 0.0005495274681986, "max": 0.0615954947968324, "count": 58 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 58 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 58 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 58 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 58 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 58 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 58 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717444594", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717447320" }, "total": 2725.934264701, "count": 1, "self": 0.13758261400016636, "children": { "run_training.setup": { "total": 0.06685330499999509, "count": 1, "self": 0.06685330499999509 }, "TrainerController.start_learning": { "total": 2725.729828782, "count": 1, "self": 1.9225073879970296, "children": { "TrainerController._reset_env": { "total": 3.656940650000138, "count": 7, "self": 3.656940650000138 }, "TrainerController.advance": { "total": 2719.7633354740024, "count": 81661, "self": 2.082915705114374, "children": { "env_step": { "total": 2200.55965069901, "count": 81661, "self": 1676.967132833107, "children": { "SubprocessEnvManager._take_step": { "total": 522.4249811439598, "count": 81661, "self": 16.175533431941176, "children": { "TorchPolicy.evaluate": { "total": 506.24944771201865, "count": 159978, "self": 506.24944771201865 } } }, "workers": { "total": 1.1675367219431791, "count": 81661, "self": 0.0, "children": { "worker_root": { "total": 2720.472810753042, "count": 81661, "is_parallel": true, "self": 1312.1720663330736, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061693979999972726, "count": 2, "is_parallel": true, "self": 0.003932343000087712, "children": { "_process_rank_one_or_two_observation": { "total": 0.00223705499990956, "count": 8, "is_parallel": true, "self": 0.00223705499990956 } } }, "UnityEnvironment.step": { "total": 0.039695700000038414, "count": 1, "is_parallel": true, "self": 0.0011881120001362433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008654870000555093, "count": 1, "is_parallel": true, "self": 0.0008654870000555093 }, "communicator.exchange": { "total": 0.03424549599992588, "count": 1, "is_parallel": true, "self": 0.03424549599992588 }, "steps_from_proto": { "total": 0.0033966049999207826, "count": 2, "is_parallel": true, "self": 0.000648830999580241, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027477740003405415, "count": 8, "is_parallel": true, "self": 0.0027477740003405415 } } } } } } }, "UnityEnvironment.step": { "total": 1408.2878612979682, "count": 81660, "is_parallel": true, "self": 86.80044462888077, "children": { "UnityEnvironment._generate_step_input": { "total": 60.041113616990174, "count": 81660, "is_parallel": true, "self": 60.041113616990174 }, "communicator.exchange": { "total": 989.0573466660942, "count": 81660, "is_parallel": true, "self": 989.0573466660942 }, "steps_from_proto": { "total": 272.3889563860031, "count": 163320, "is_parallel": true, "self": 44.932211983203956, "children": { "_process_rank_one_or_two_observation": { "total": 227.45674440279913, "count": 653280, "is_parallel": true, "self": 227.45674440279913 } } } } }, "steps_from_proto": { "total": 0.012883121999948344, "count": 12, "is_parallel": true, "self": 0.0027552960009415983, "children": { "_process_rank_one_or_two_observation": { "total": 0.010127825999006745, "count": 48, "is_parallel": true, "self": 0.010127825999006745 } } } } } } } } }, "trainer_advance": { "total": 517.120769069878, "count": 81661, "self": 16.27377930387945, "children": { "process_trajectory": { "total": 159.97673368699827, "count": 81661, "self": 159.34977788699837, "children": { "RLTrainer._checkpoint": { "total": 0.6269557999999051, "count": 2, "self": 0.6269557999999051 } } }, "_update_policy": { "total": 340.8702560790002, "count": 58, "self": 203.80017319900503, "children": { "TorchPOCAOptimizer.update": { "total": 137.0700828799952, "count": 1749, "self": 137.0700828799952 } } } } } } }, "trainer_threads": { "total": 1.362000148219522e-06, "count": 1, "self": 1.362000148219522e-06 }, "TrainerController._save_models": { "total": 0.38704390800012334, "count": 1, "self": 0.002530480000132229, "children": { "RLTrainer._checkpoint": { "total": 0.3845134279999911, "count": 1, "self": 0.3845134279999911 } } } } } } }