{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6969166994094849, "min": 1.6600289344787598, "max": 3.2957608699798584, "count": 716 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32200.69140625, "min": 24688.013671875, "max": 116438.890625, "count": 716 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.17948717948718, "min": 41.55263157894737, "max": 999.0, "count": 716 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19088.0, "min": 13220.0, "max": 29168.0, "count": 716 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1620.4971049478559, "min": 1196.3410541923008, "max": 1642.0822759048187, "count": 714 }, "SoccerTwos.Self-play.ELO.sum": { "value": 252797.5483718655, "min": 2394.5245533924726, "max": 366864.2800499807, "count": 714 }, "SoccerTwos.Step.mean": { "value": 7159779.0, "min": 9600.0, "max": 7159779.0, "count": 716 }, "SoccerTwos.Step.sum": { "value": 7159779.0, "min": 9600.0, "max": 7159779.0, "count": 716 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03972044959664345, "min": -0.11577586084604263, "max": 0.17879104614257812, "count": 716 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.236110687255859, "min": -21.881637573242188, "max": 30.8237247467041, "count": 716 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03798370808362961, "min": -0.11704134196043015, "max": 0.18601049482822418, "count": 716 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.963442325592041, "min": -22.120813369750977, "max": 30.830636978149414, "count": 716 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 716 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 716 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18272102182837807, "min": -0.5435230777813838, "max": 0.4047047637757801, "count": 716 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -28.68720042705536, "min": -56.80580013990402, "max": 72.85040009021759, "count": 716 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18272102182837807, "min": -0.5435230777813838, "max": 0.4047047637757801, "count": 716 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -28.68720042705536, "min": -56.80580013990402, "max": 72.85040009021759, "count": 716 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 716 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 716 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018955567812857527, "min": 0.011760395910823718, "max": 0.02439175733986, "count": 345 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018955567812857527, "min": 0.011760395910823718, "max": 0.02439175733986, "count": 345 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09430747206012408, "min": 0.001318148347005869, "max": 0.12452329446872075, "count": 345 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09430747206012408, "min": 0.001318148347005869, "max": 0.12452329446872075, "count": 345 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09539426416158676, "min": 0.0013465542113408446, "max": 0.1273934985200564, "count": 345 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09539426416158676, "min": 0.0013465542113408446, "max": 0.1273934985200564, "count": 345 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 345 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 345 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 345 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 345 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 345 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 345 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691382831", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\KIIT\\anaconda3\\envs\\soccertwos\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1691419952" }, "total": 37120.8491212, "count": 1, "self": 0.30677389999618754, "children": { "run_training.setup": { "total": 0.08919880000000013, "count": 1, "self": 0.08919880000000013 }, "TrainerController.start_learning": { "total": 37120.453148500004, "count": 1, "self": 20.33770420008659, "children": { "TrainerController._reset_env": { "total": 13.694396899995077, "count": 36, "self": 13.694396899995077 }, "TrainerController.advance": { "total": 37086.261934099915, "count": 492424, "self": 22.40536360043916, "children": { "env_step": { "total": 15485.984040899692, "count": 492424, "self": 12373.582369201213, "children": { "SubprocessEnvManager._take_step": { "total": 3100.000899998611, "count": 492424, "self": 117.0006025992243, "children": { "TorchPolicy.evaluate": { "total": 2983.000297399387, "count": 903100, "self": 2983.000297399387 } } }, "workers": { "total": 12.40077169986739, "count": 492424, "self": 0.0, "children": { "worker_root": { "total": 37075.89335389997, "count": 492424, "is_parallel": true, "self": 26897.2692583011, "children": { "steps_from_proto": { "total": 0.10038329999326834, "count": 72, "is_parallel": true, "self": 0.0196578000123786, "children": { "_process_rank_one_or_two_observation": { "total": 0.08072549998088974, "count": 288, "is_parallel": true, "self": 0.08072549998088974 } } }, "UnityEnvironment.step": { "total": 10178.523712298875, "count": 492424, "is_parallel": true, "self": 524.8324196028625, "children": { "UnityEnvironment._generate_step_input": { "total": 389.91999889780186, "count": 492424, "is_parallel": true, "self": 389.91999889780186 }, "communicator.exchange": { "total": 7672.752460799156, "count": 492424, "is_parallel": true, "self": 7672.752460799156 }, "steps_from_proto": { "total": 1591.018832999055, "count": 984848, "is_parallel": true, "self": 314.2547457979849, "children": { "_process_rank_one_or_two_observation": { "total": 1276.76408720107, "count": 3939392, "is_parallel": true, "self": 1276.76408720107 } } } } } } } } } } }, "trainer_advance": { "total": 21577.872529599783, "count": 492423, "self": 142.06196080096197, "children": { "process_trajectory": { "total": 3511.3798764988283, "count": 492423, "self": 3506.947726598819, "children": { "RLTrainer._checkpoint": { "total": 4.432149900009563, "count": 14, "self": 4.432149900009563 } } }, "_update_policy": { "total": 17924.430692299993, "count": 346, "self": 1726.6294520000083, "children": { "TorchPOCAOptimizer.update": { "total": 16197.801240299985, "count": 10380, "self": 16197.801240299985 } } } } } } }, "trainer_threads": { "total": 1.400003384333104e-06, "count": 1, "self": 1.400003384333104e-06 }, "TrainerController._save_models": { "total": 0.15911190000042552, "count": 1, "self": 0.007620400006999262, "children": { "RLTrainer._checkpoint": { "total": 0.15149149999342626, "count": 1, "self": 0.15149149999342626 } } } } } } }