{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4617689847946167, "min": 1.332874059677124, "max": 3.2957069873809814, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27832.08203125, "min": 21882.611328125, "max": 118871.578125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.49295774647888, "min": 40.5, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19736.0, "min": 3996.0, "max": 31004.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1650.5768481760022, "min": 1192.1416974634824, "max": 1707.1835606316117, "count": 4997 }, "SoccerTwos.Self-play.ELO.sum": { "value": 234381.9124409923, "min": 2384.283394926965, "max": 390961.1526288972, "count": 4997 }, "SoccerTwos.Step.mean": { "value": 49999951.0, "min": 9786.0, "max": 49999951.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999951.0, "min": 9786.0, "max": 49999951.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.012258904054760933, "min": -0.148080512881279, "max": 0.16084472835063934, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.7407643795013428, "min": -28.43145751953125, "max": 34.14482879638672, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.013871767558157444, "min": -0.14815695583820343, "max": 0.15961363911628723, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.9697909355163574, "min": -28.446134567260742, "max": 33.1370964050293, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08832675974133988, "min": -0.6386888888147142, "max": 0.5193379254176699, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.542399883270264, "min": -80.83239984512329, "max": 63.52080023288727, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08832675974133988, "min": -0.6386888888147142, "max": 0.5193379254176699, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.542399883270264, "min": -80.83239984512329, "max": 63.52080023288727, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017822199609630236, "min": 0.009487322757316482, "max": 0.02624323091780146, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017822199609630236, "min": 0.009487322757316482, "max": 0.02624323091780146, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09293877705931664, "min": 0.0005154974768326307, "max": 0.126951323201259, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09293877705931664, "min": 0.0005154974768326307, "max": 0.126951323201259, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09431866630911827, "min": 0.000516512922088926, "max": 0.12884828920165697, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09431866630911827, "min": 0.000516512922088926, "max": 0.12884828920165697, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695908809", "python_version": "3.9.18 (main, Sep 11 2023, 13:41:44) \n[GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696005305" }, "total": 96496.132617792, "count": 1, "self": 0.3784213839971926, "children": { "run_training.setup": { "total": 0.007320440003240947, "count": 1, "self": 0.007320440003240947 }, "TrainerController.start_learning": { "total": 96495.746875968, "count": 1, "self": 57.77581728520454, "children": { "TrainerController._reset_env": { "total": 3.8935154349201184, "count": 250, "self": 3.8935154349201184 }, "TrainerController.advance": { "total": 96433.8697349739, "count": 3447379, "self": 63.16692418958701, "children": { "env_step": { "total": 46806.88848410416, "count": 3447379, "self": 41522.558002341044, "children": { "SubprocessEnvManager._take_step": { "total": 5246.375490510603, "count": 3447379, "self": 286.0012961551147, "children": { "TorchPolicy.evaluate": { "total": 4960.374194355489, "count": 6281010, "self": 4960.374194355489 } } }, "workers": { "total": 37.954991252514446, "count": 3447379, "self": 0.0, "children": { "worker_root": { "total": 96363.02297746808, "count": 3447379, "is_parallel": true, "self": 60541.84459547478, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014306179982668255, "count": 2, "is_parallel": true, "self": 0.00039618698792764917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010344310103391763, "count": 8, "is_parallel": true, "self": 0.0010344310103391763 } } }, "UnityEnvironment.step": { "total": 0.018666894000489265, "count": 1, "is_parallel": true, "self": 0.0003737270017154515, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002466320001985878, "count": 1, "is_parallel": true, "self": 0.0002466320001985878 }, "communicator.exchange": { "total": 0.016957683001237456, "count": 1, "is_parallel": true, "self": 0.016957683001237456 }, "steps_from_proto": { "total": 0.0010888519973377697, "count": 2, "is_parallel": true, "self": 0.00029736200303887017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007914899942988995, "count": 8, "is_parallel": true, "self": 0.0007914899942988995 } } } } } } }, "UnityEnvironment.step": { "total": 35820.938156066215, "count": 3447378, "is_parallel": true, "self": 1049.2069826879306, "children": { "UnityEnvironment._generate_step_input": { "total": 618.7168775363389, "count": 3447378, "is_parallel": true, "self": 618.7168775363389 }, "communicator.exchange": { "total": 31117.198143229813, "count": 3447378, "is_parallel": true, "self": 31117.198143229813 }, "steps_from_proto": { "total": 3035.8161526121294, "count": 6894756, "is_parallel": true, "self": 619.946729455336, "children": { "_process_rank_one_or_two_observation": { "total": 2415.8694231567933, "count": 27579024, "is_parallel": true, "self": 2415.8694231567933 } } } } }, "steps_from_proto": { "total": 0.24022592708206503, "count": 498, "is_parallel": true, "self": 0.0490387380195898, "children": { "_process_rank_one_or_two_observation": { "total": 0.19118718906247523, "count": 1992, "is_parallel": true, "self": 0.19118718906247523 } } } } } } } } }, "trainer_advance": { "total": 49563.81432668014, "count": 3447379, "self": 463.47807261179696, "children": { "process_trajectory": { "total": 5812.134094873258, "count": 3447379, "self": 5800.489614529342, "children": { "RLTrainer._checkpoint": { "total": 11.644480343915347, "count": 100, "self": 11.644480343915347 } } }, "_update_policy": { "total": 43288.20215919509, "count": 2424, "self": 4643.756068403927, "children": { "TorchPOCAOptimizer.update": { "total": 38644.44609079116, "count": 72732, "self": 38644.44609079116 } } } } } } }, "trainer_threads": { "total": 5.669862730428576e-07, "count": 1, "self": 5.669862730428576e-07 }, "TrainerController._save_models": { "total": 0.20780770700366702, "count": 1, "self": 0.00687030800327193, "children": { "RLTrainer._checkpoint": { "total": 0.2009373990003951, "count": 1, "self": 0.2009373990003951 } } } } } } }