{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2167279720306396, "min": 3.1973202228546143, "max": 3.2956995964050293, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 102935.296875, "min": 37185.703125, "max": 130729.421875, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 558.375, "min": 355.2307692307692, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17868.0, "min": 15068.0, "max": 25260.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.187218738631, "min": 1194.187218738631, "max": 1203.4016242819084, "count": 39 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2388.374437477262, "min": 2388.374437477262, "max": 23929.033746886005, "count": 39 }, "SoccerTwos.Step.mean": { "value": 499552.0, "min": 9648.0, "max": 499552.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499552.0, "min": 9648.0, "max": 499552.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00390473660081625, "min": -0.08126641064882278, "max": 0.014773346483707428, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.06638052314519882, "min": -1.537827968597412, "max": 0.2500327229499817, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0042207203805446625, "min": -0.07779227942228317, "max": 0.01406838372349739, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07175225019454956, "min": -1.4383354187011719, "max": 0.23916251957416534, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.4201750010251999, "max": 0.3598666747411092, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.921999998390675, "max": 5.398000121116638, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4201750010251999, "max": 0.3598666747411092, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.921999998390675, "max": 5.398000121116638, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015917055184642474, "min": 0.011932552664075047, "max": 0.02313203196778583, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015917055184642474, "min": 0.011932552664075047, "max": 0.02313203196778583, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008109367045108229, "min": 3.57876278940239e-05, "max": 0.005951197103907665, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008109367045108229, "min": 3.57876278940239e-05, "max": 0.005951197103907665, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008106520489188066, "min": 3.531726955164534e-05, "max": 0.005981516093015671, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0008106520489188066, "min": 3.531726955164534e-05, "max": 0.005981516093015671, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719070914", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/diego/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719071442" }, "total": 528.704971621999, "count": 1, "self": 0.21809306699651643, "children": { "run_training.setup": { "total": 0.030361275999894133, "count": 1, "self": 0.030361275999894133 }, "TrainerController.start_learning": { "total": 528.4565172790026, "count": 1, "self": 0.5282690684616682, "children": { "TrainerController._reset_env": { "total": 2.1051965660008136, "count": 13, "self": 2.1051965660008136 }, "TrainerController.advance": { "total": 525.6977479285451, "count": 37164, "self": 0.5636299799298286, "children": { "env_step": { "total": 423.05774586966436, "count": 37164, "self": 309.7807341303487, "children": { "SubprocessEnvManager._take_step": { "total": 112.92941606832755, "count": 37164, "self": 3.1370184365041496, "children": { "TorchPolicy.evaluate": { "total": 109.7923976318234, "count": 73750, "self": 109.7923976318234 } } }, "workers": { "total": 0.34759567098808475, "count": 37164, "self": 0.0, "children": { "worker_root": { "total": 527.4745943693088, "count": 37164, "is_parallel": true, "self": 281.41875222134695, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014076890001888387, "count": 2, "is_parallel": true, "self": 0.0003525610009091906, "children": { "_process_rank_one_or_two_observation": { "total": 0.001055127999279648, "count": 8, "is_parallel": true, "self": 0.001055127999279648 } } }, "UnityEnvironment.step": { "total": 0.015537252998910844, "count": 1, "is_parallel": true, "self": 0.0003910280029231217, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002788439996948, "count": 1, "is_parallel": true, "self": 0.0002788439996948 }, "communicator.exchange": { "total": 0.013840812996932073, "count": 1, "is_parallel": true, "self": 0.013840812996932073 }, "steps_from_proto": { "total": 0.00102656799936085, "count": 2, "is_parallel": true, "self": 0.0002212470026279334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008053209967329167, "count": 8, "is_parallel": true, "self": 0.0008053209967329167 } } } } } } }, "UnityEnvironment.step": { "total": 246.04431799796657, "count": 37163, "is_parallel": true, "self": 13.048685674148146, "children": { "UnityEnvironment._generate_step_input": { "total": 9.000386016799894, "count": 37163, "is_parallel": true, "self": 9.000386016799894 }, "communicator.exchange": { "total": 187.2834473853436, "count": 37163, "is_parallel": true, "self": 187.2834473853436 }, "steps_from_proto": { "total": 36.71179892167493, "count": 74326, "is_parallel": true, "self": 7.200647920806659, "children": { "_process_rank_one_or_two_observation": { "total": 29.511151000868267, "count": 297304, "is_parallel": true, "self": 29.511151000868267 } } } } }, "steps_from_proto": { "total": 0.011524149995238986, "count": 24, "is_parallel": true, "self": 0.002306710015545832, "children": { "_process_rank_one_or_two_observation": { "total": 0.009217439979693154, "count": 96, "is_parallel": true, "self": 0.009217439979693154 } } } } } } } } }, "trainer_advance": { "total": 102.07637207895095, "count": 37164, "self": 4.291560851252143, "children": { "process_trajectory": { "total": 26.002775756704068, "count": 37164, "self": 25.9022926027028, "children": { "RLTrainer._checkpoint": { "total": 0.1004831540012674, "count": 1, "self": 0.1004831540012674 } } }, "_update_policy": { "total": 71.78203547099474, "count": 23, "self": 38.797311159993114, "children": { "TorchPOCAOptimizer.update": { "total": 32.98472431100163, "count": 690, "self": 32.98472431100163 } } } } } } }, "trainer_threads": { "total": 4.839967004954815e-07, "count": 1, "self": 4.839967004954815e-07 }, "TrainerController._save_models": { "total": 0.12530323199825943, "count": 1, "self": 0.001199418995383894, "children": { "RLTrainer._checkpoint": { "total": 0.12410381300287554, "count": 1, "self": 0.12410381300287554 } } } } } } }