{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.199147939682007, "min": 2.1816043853759766, "max": 2.353656768798828, "count": 687 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46094.140625, "min": 22571.28515625, "max": 53690.65234375, "count": 687 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.13888888888889, "min": 41.58474576271186, "max": 88.49090909090908, "count": 687 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20200.0, "min": 7220.0, "max": 20976.0, "count": 687 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1500.3859526991957, "min": 1372.4336771187784, "max": 1515.4123165632393, "count": 687 }, "SoccerTwos.Self-play.ELO.sum": { "value": 216055.5771886842, "min": 107343.02375037539, "max": 338336.3171132483, "count": 687 }, "SoccerTwos.Step.mean": { "value": 49999915.0, "min": 43139889.0, "max": 49999915.0, "count": 687 }, "SoccerTwos.Step.sum": { "value": 49999915.0, "min": 43139889.0, "max": 49999915.0, "count": 687 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.031451527029275894, "min": -0.13354863226413727, "max": 0.0982910543680191, "count": 687 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.529019832611084, "min": -22.04212188720703, "max": 14.252202987670898, "count": 687 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026619238778948784, "min": -0.13915225863456726, "max": 0.09924395382404327, "count": 687 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.8331704139709473, "min": -23.291719436645508, "max": 14.390373229980469, "count": 687 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 687 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 687 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06341944386561711, "min": -0.3395951223082659, "max": 0.29721103454458303, "count": 687 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.132399916648865, "min": -55.70960009098053, "max": 51.130799770355225, "count": 687 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06341944386561711, "min": -0.3395951223082659, "max": 0.29721103454458303, "count": 687 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.132399916648865, "min": -55.70960009098053, "max": 51.130799770355225, "count": 687 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 687 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 687 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014173012745838301, "min": 0.011419490334810689, "max": 0.023585874183724324, "count": 333 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014173012745838301, "min": 0.011419490334810689, "max": 0.023585874183724324, "count": 333 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11195754905541738, "min": 0.08395632058382034, "max": 0.12328578556577365, "count": 333 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11195754905541738, "min": 0.08395632058382034, "max": 0.12328578556577365, "count": 333 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1126358762383461, "min": 0.08434434235095978, "max": 0.12504474098483723, "count": 333 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1126358762383461, "min": 0.08434434235095978, "max": 0.12504474098483723, "count": 333 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.999999999999999e-05, "min": 4.999999999999999e-05, "max": 4.999999999999999e-05, "count": 333 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.999999999999999e-05, "min": 4.999999999999999e-05, "max": 4.999999999999999e-05, "count": 333 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.15000000000000002, "min": 0.15000000000000002, "max": 0.15000000000000002, "count": 333 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.15000000000000002, "min": 0.15000000000000002, "max": 0.15000000000000002, "count": 333 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 333 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 333 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680557842", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/u/miniconda3/envs/huggingface-unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1680569131" }, "total": 11289.190464044, "count": 1, "self": 0.1681572679990495, "children": { "run_training.setup": { "total": 0.009920802999658918, "count": 1, "self": 0.009920802999658918 }, "TrainerController.start_learning": { "total": 11289.012385973001, "count": 1, "self": 5.444020750352138, "children": { "TrainerController._reset_env": { "total": 3.915881820998038, "count": 36, "self": 3.915881820998038 }, "TrainerController.advance": { "total": 11279.518785961653, "count": 474960, "self": 5.141610182959994, "children": { "env_step": { "total": 8533.210569556382, "count": 474960, "self": 4592.567577960335, "children": { "SubprocessEnvManager._take_step": { "total": 3937.353161764495, "count": 474960, "self": 33.035020673268264, "children": { "TorchPolicy.evaluate": { "total": 3904.3181410912266, "count": 861448, "self": 3904.3181410912266 } } }, "workers": { "total": 3.289829831552197, "count": 474960, "self": 0.0, "children": { "worker_root": { "total": 11272.416131767537, "count": 474960, "is_parallel": true, "self": 7259.399130238302, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018770259994198568, "count": 2, "is_parallel": true, "self": 0.0008655679994262755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010114579999935813, "count": 8, "is_parallel": true, "self": 0.0010114579999935813 } } }, "UnityEnvironment.step": { "total": 0.017568834000485367, "count": 1, "is_parallel": true, "self": 0.00033144499957415974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000255146000199602, "count": 1, "is_parallel": true, "self": 0.000255146000199602 }, "communicator.exchange": { "total": 0.016013004999877012, "count": 1, "is_parallel": true, "self": 0.016013004999877012 }, "steps_from_proto": { "total": 0.0009692380008345935, "count": 2, "is_parallel": true, "self": 0.00019651900220196694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007727189986326266, "count": 8, "is_parallel": true, "self": 0.0007727189986326266 } } } } } } }, "steps_from_proto": { "total": 0.033808206992034684, "count": 70, "is_parallel": true, "self": 0.006709429997499683, "children": { "_process_rank_one_or_two_observation": { "total": 0.027098776994535, "count": 280, "is_parallel": true, "self": 0.027098776994535 } } }, "UnityEnvironment.step": { "total": 4012.983193322243, "count": 474959, "is_parallel": true, "self": 148.3840445602109, "children": { "UnityEnvironment._generate_step_input": { "total": 89.28915272503491, "count": 474959, "is_parallel": true, "self": 89.28915272503491 }, "communicator.exchange": { "total": 3357.7978171673203, "count": 474959, "is_parallel": true, "self": 3357.7978171673203 }, "steps_from_proto": { "total": 417.512178869677, "count": 949918, "is_parallel": true, "self": 81.62929160402109, "children": { "_process_rank_one_or_two_observation": { "total": 335.8828872656559, "count": 3799672, "is_parallel": true, "self": 335.8828872656559 } } } } } } } } } } }, "trainer_advance": { "total": 2741.166606222311, "count": 474960, "self": 41.21544992764484, "children": { "process_trajectory": { "total": 1664.5799107626653, "count": 474960, "self": 1662.281493237665, "children": { "RLTrainer._checkpoint": { "total": 2.298417525000332, "count": 14, "self": 2.298417525000332 } } }, "_update_policy": { "total": 1035.371245532001, "count": 333, "self": 591.2800377140002, "children": { "TorchPOCAOptimizer.update": { "total": 444.09120781800084, "count": 9990, "self": 444.09120781800084 } } } } } } }, "trainer_threads": { "total": 5.299989425111562e-07, "count": 1, "self": 5.299989425111562e-07 }, "TrainerController._save_models": { "total": 0.13369690999934392, "count": 1, "self": 0.0008389189988520229, "children": { "RLTrainer._checkpoint": { "total": 0.1328579910004919, "count": 1, "self": 0.1328579910004919 } } } } } } }