{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9140814542770386, "min": 1.8864214420318604, "max": 3.295835018157959, "count": 515 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39751.64453125, "min": 5685.056640625, "max": 143504.75, "count": 515 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.77906976744186, "min": 40.890756302521005, "max": 999.0, "count": 515 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19876.0, "min": 12348.0, "max": 31244.0, "count": 515 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1533.0822119962954, "min": 1197.5459124621675, "max": 1540.9759345148252, "count": 501 }, "SoccerTwos.Self-play.ELO.sum": { "value": 263690.1404633628, "min": 2396.0820640005386, "max": 356824.16796070227, "count": 501 }, "SoccerTwos.Step.mean": { "value": 5149994.0, "min": 9638.0, "max": 5149994.0, "count": 515 }, "SoccerTwos.Step.sum": { "value": 5149994.0, "min": 9638.0, "max": 5149994.0, "count": 515 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.010578186251223087, "min": -0.08221328258514404, "max": 0.15073518455028534, "count": 515 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.8194479942321777, "min": -15.013703346252441, "max": 18.658824920654297, "count": 515 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009976166300475597, "min": -0.0881015807390213, "max": 0.15645430982112885, "count": 515 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.7159005403518677, "min": -15.946386337280273, "max": 18.774517059326172, "count": 515 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 515 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 515 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04919302255608315, "min": -0.6293083348621925, "max": 0.4518193568914167, "count": 515 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.461199879646301, "min": -68.13879990577698, "max": 45.9297998547554, "count": 515 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04919302255608315, "min": -0.6293083348621925, "max": 0.4518193568914167, "count": 515 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.461199879646301, "min": -68.13879990577698, "max": 45.9297998547554, "count": 515 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 515 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 515 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016515966093478104, "min": 0.010849756060633809, "max": 0.023399870352780756, "count": 247 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016515966093478104, "min": 0.010849756060633809, "max": 0.023399870352780756, "count": 247 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11570895413557689, "min": 0.0002333417687623296, "max": 0.13196071659525235, "count": 247 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11570895413557689, "min": 0.0002333417687623296, "max": 0.13196071659525235, "count": 247 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11769971524675688, "min": 0.00023309608908069399, "max": 0.13395524819691976, "count": 247 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11769971524675688, "min": 0.00023309608908069399, "max": 0.13395524819691976, "count": 247 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 247 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 247 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 247 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 247 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 247 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 247 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730189625", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/gamma/anaconda3/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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1730197519" }, "total": 7893.7553051999985, "count": 1, "self": 0.1445342159968277, "children": { "run_training.setup": { "total": 0.007312195000849897, "count": 1, "self": 0.007312195000849897 }, "TrainerController.start_learning": { "total": 7893.603458789001, "count": 1, "self": 7.188664224846434, "children": { "TrainerController._reset_env": { "total": 2.6877606729922263, "count": 52, "self": 2.6877606729922263 }, "TrainerController.advance": { "total": 7883.602293215161, "count": 353437, "self": 7.448443998739094, "children": { "env_step": { "total": 6198.244574607146, "count": 353437, "self": 4562.80871321779, "children": { "SubprocessEnvManager._take_step": { "total": 1631.010823737619, "count": 353437, "self": 46.170941866042995, "children": { "TorchPolicy.evaluate": { "total": 1584.839881871576, "count": 659322, "self": 1584.839881871576 } } }, "workers": { "total": 4.425037651737512, "count": 353436, "self": 0.0, "children": { "worker_root": { "total": 7884.920634769955, "count": 353436, "is_parallel": true, "self": 4133.006983564104, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00114961500003119, "count": 2, "is_parallel": true, "self": 0.0002833700036717346, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008662449963594554, "count": 8, "is_parallel": true, "self": 0.0008662449963594554 } } }, "UnityEnvironment.step": { "total": 0.014098433999606641, "count": 1, "is_parallel": true, "self": 0.0003312819990242133, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023107299966795836, "count": 1, "is_parallel": true, "self": 0.00023107299966795836 }, "communicator.exchange": { "total": 0.012526913000328932, "count": 1, "is_parallel": true, "self": 0.012526913000328932 }, "steps_from_proto": { "total": 0.0010091660005855374, "count": 2, "is_parallel": true, "self": 0.0001971159999811789, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008120500006043585, "count": 8, "is_parallel": true, "self": 0.0008120500006043585 } } } } } } }, "UnityEnvironment.step": { "total": 3751.8333752188446, "count": 353435, "is_parallel": true, "self": 195.05821750994255, "children": { "UnityEnvironment._generate_step_input": { "total": 113.27530648295215, "count": 353435, "is_parallel": true, "self": 113.27530648295215 }, "communicator.exchange": { "total": 2923.869950263441, "count": 353435, "is_parallel": true, "self": 2923.869950263441 }, "steps_from_proto": { "total": 519.629900962509, "count": 706870, "is_parallel": true, "self": 95.98677193328695, "children": { "_process_rank_one_or_two_observation": { "total": 423.6431290292221, "count": 2827480, "is_parallel": true, "self": 423.6431290292221 } } } } }, "steps_from_proto": { "total": 0.08027598700573435, "count": 102, "is_parallel": true, "self": 0.014995029019701178, "children": { "_process_rank_one_or_two_observation": { "total": 0.06528095798603317, "count": 408, "is_parallel": true, "self": 0.06528095798603317 } } } } } } } } }, "trainer_advance": { "total": 1677.9092746092756, "count": 353436, "self": 44.995777109910705, "children": { "process_trajectory": { "total": 767.9270163023793, "count": 353436, "self": 766.5759700233793, "children": { "RLTrainer._checkpoint": { "total": 1.351046279000002, "count": 10, "self": 1.351046279000002 } } }, "_update_policy": { "total": 864.9864811969856, "count": 247, "self": 556.4801677838786, "children": { "TorchPOCAOptimizer.update": { "total": 308.5063134131069, "count": 7410, "self": 308.5063134131069 } } } } } } }, "trainer_threads": { "total": 1.1129995982628316e-06, "count": 1, "self": 1.1129995982628316e-06 }, "TrainerController._save_models": { "total": 0.12473956300163991, "count": 1, "self": 0.001506814001913881, "children": { "RLTrainer._checkpoint": { "total": 0.12323274899972603, "count": 1, "self": 0.12323274899972603 } } } } } } }