| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.6974644660949707, | |
| "min": 1.6479068994522095, | |
| "max": 1.896829605102539, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 35415.8984375, | |
| "min": 28536.375, | |
| "max": 40821.8828125, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 54.78021978021978, | |
| "min": 45.48598130841121, | |
| "max": 93.90566037735849, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19940.0, | |
| "min": 18188.0, | |
| "max": 21376.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1586.4362070420182, | |
| "min": 1540.313808969222, | |
| "max": 1614.8667785937826, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 288731.3896816473, | |
| "min": 166080.3791611248, | |
| "max": 342651.52787535306, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 14999834.0, | |
| "min": 10009998.0, | |
| "max": 14999834.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 14999834.0, | |
| "min": 10009998.0, | |
| "max": 14999834.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.09347043931484222, | |
| "min": -0.10996756702661514, | |
| "max": 0.07917854189872742, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -16.918149948120117, | |
| "min": -18.584518432617188, | |
| "max": 14.014601707458496, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0938849151134491, | |
| "min": -0.11217296868562698, | |
| "max": 0.07936329394578934, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -16.9931697845459, | |
| "min": -18.79776382446289, | |
| "max": 13.77039909362793, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.09913370227286829, | |
| "min": -0.3590155045191447, | |
| "max": 0.31450215818213045, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -17.94320011138916, | |
| "min": -51.055600464344025, | |
| "max": 50.304800271987915, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.09913370227286829, | |
| "min": -0.3590155045191447, | |
| "max": 0.31450215818213045, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -17.94320011138916, | |
| "min": -51.055600464344025, | |
| "max": 50.304800271987915, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.013691309865680523, | |
| "min": 0.010207320038656082, | |
| "max": 0.025986198308722428, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.013691309865680523, | |
| "min": 0.010207320038656082, | |
| "max": 0.025986198308722428, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.11231135825316112, | |
| "min": 0.07683478419979413, | |
| "max": 0.1216113289197286, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.11231135825316112, | |
| "min": 0.07683478419979413, | |
| "max": 0.1216113289197286, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.11509122302134832, | |
| "min": 0.07745104084412256, | |
| "max": 0.12338073030114174, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.11509122302134832, | |
| "min": 0.07745104084412256, | |
| "max": 0.12338073030114174, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 242 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 242 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1677257660", | |
| "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "C:\\Users\\leonh\\anaconda3\\envs\\rl_course\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1.13.1+cpu", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1677275404" | |
| }, | |
| "total": 17743.3639587, | |
| "count": 1, | |
| "self": 0.3233462000025611, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.10402470000000008, | |
| "count": 1, | |
| "self": 0.10402470000000008 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 17742.9365878, | |
| "count": 1, | |
| "self": 7.322832100213418, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.791751799999756, | |
| "count": 16, | |
| "self": 3.791751799999756 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 17731.70783189979, | |
| "count": 345148, | |
| "self": 6.805752999469405, | |
| "children": { | |
| "env_step": { | |
| "total": 6258.933678300444, | |
| "count": 345148, | |
| "self": 5078.930546300986, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1175.3040134000476, | |
| "count": 345148, | |
| "self": 39.98794329983343, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1135.3160701002141, | |
| "count": 626460, | |
| "self": 1135.3160701002141 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 4.699118599410042, | |
| "count": 345148, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 17725.01145240032, | |
| "count": 345148, | |
| "is_parallel": true, | |
| "self": 13473.047958101204, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.029470499995648325, | |
| "count": 32, | |
| "is_parallel": true, | |
| "self": 0.005261399998012006, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.02420909999763632, | |
| "count": 128, | |
| "is_parallel": true, | |
| "self": 0.02420909999763632 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 4251.934023799118, | |
| "count": 345148, | |
| "is_parallel": true, | |
| "self": 188.7873391995995, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 140.90055439993918, | |
| "count": 345148, | |
| "is_parallel": true, | |
| "self": 140.90055439993918 | |
| }, | |
| "communicator.exchange": { | |
| "total": 3327.546066999894, | |
| "count": 345148, | |
| "is_parallel": true, | |
| "self": 3327.546066999894 | |
| }, | |
| "steps_from_proto": { | |
| "total": 594.7000631996857, | |
| "count": 690296, | |
| "is_parallel": true, | |
| "self": 107.05366169907165, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 487.64640150061405, | |
| "count": 2761184, | |
| "is_parallel": true, | |
| "self": 487.64640150061405 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 11465.968400599877, | |
| "count": 345148, | |
| "self": 65.8435991999122, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 1772.7973054999507, | |
| "count": 345148, | |
| "self": 1771.5240645999481, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.27324090000252, | |
| "count": 10, | |
| "self": 1.27324090000252 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 9627.327495900014, | |
| "count": 242, | |
| "self": 777.1713052999894, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 8850.156190600024, | |
| "count": 7260, | |
| "self": 8850.156190600024 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1999982234556228e-06, | |
| "count": 1, | |
| "self": 1.1999982234556228e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.11417079999955604, | |
| "count": 1, | |
| "self": 0.0024827999986882787, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.11168800000086776, | |
| "count": 1, | |
| "self": 0.11168800000086776 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |