| { |
| "name": "root", |
| "gauges": { |
| "SoccerTwos.Policy.Entropy.mean": { |
| "value": 1.438185214996338, |
| "min": 1.2871428728103638, |
| "max": 3.295762777328491, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.Entropy.sum": { |
| "value": 29546.078125, |
| "min": 18158.86328125, |
| "max": 128507.140625, |
| "count": 5000 |
| }, |
| "SoccerTwos.Environment.EpisodeLength.mean": { |
| "value": 80.08333333333333, |
| "min": 42.663716814159294, |
| "max": 999.0, |
| "count": 5000 |
| }, |
| "SoccerTwos.Environment.EpisodeLength.sum": { |
| "value": 19220.0, |
| "min": 5000.0, |
| "max": 29028.0, |
| "count": 5000 |
| }, |
| "SoccerTwos.Self-play.ELO.mean": { |
| "value": 1725.4868357549199, |
| "min": 1193.015162420967, |
| "max": 1786.8978130593764, |
| "count": 4983 |
| }, |
| "SoccerTwos.Self-play.ELO.sum": { |
| "value": 207058.42029059038, |
| "min": 2386.030324841934, |
| "max": 369536.6967138476, |
| "count": 4983 |
| }, |
| "SoccerTwos.Step.mean": { |
| "value": 49999983.0, |
| "min": 9530.0, |
| "max": 49999983.0, |
| "count": 5000 |
| }, |
| "SoccerTwos.Step.sum": { |
| "value": 49999983.0, |
| "min": 9530.0, |
| "max": 49999983.0, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
| "value": -0.06711877137422562, |
| "min": -0.13952656090259552, |
| "max": 0.18732668459415436, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
| "value": -8.121371269226074, |
| "min": -26.649574279785156, |
| "max": 26.909523010253906, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.06701740622520447, |
| "min": -0.1348048895597458, |
| "max": 0.19345541298389435, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -8.109106063842773, |
| "min": -25.696334838867188, |
| "max": 28.63368797302246, |
| "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": -0.022000001481741912, |
| "min": -0.5714285714285714, |
| "max": 0.4471384584903717, |
| "count": 5000 |
| }, |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { |
| "value": -2.6620001792907715, |
| "min": -77.37279975414276, |
| "max": 56.36819976568222, |
| "count": 5000 |
| }, |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { |
| "value": -0.022000001481741912, |
| "min": -0.5714285714285714, |
| "max": 0.4471384584903717, |
| "count": 5000 |
| }, |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { |
| "value": -2.6620001792907715, |
| "min": -77.37279975414276, |
| "max": 56.36819976568222, |
| "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": 0.018539122284467642, |
| "min": 0.010676135318014228, |
| "max": 0.026691932663864767, |
| "count": 2422 |
| }, |
| "SoccerTwos.Losses.PolicyLoss.sum": { |
| "value": 0.018539122284467642, |
| "min": 0.010676135318014228, |
| "max": 0.026691932663864767, |
| "count": 2422 |
| }, |
| "SoccerTwos.Losses.ValueLoss.mean": { |
| "value": 0.07924022773901622, |
| "min": 7.781588449991734e-06, |
| "max": 0.11845265949765842, |
| "count": 2422 |
| }, |
| "SoccerTwos.Losses.ValueLoss.sum": { |
| "value": 0.07924022773901622, |
| "min": 7.781588449991734e-06, |
| "max": 0.11845265949765842, |
| "count": 2422 |
| }, |
| "SoccerTwos.Losses.BaselineLoss.mean": { |
| "value": 0.08009959459304809, |
| "min": 7.447628892502204e-06, |
| "max": 0.12023574585715929, |
| "count": 2422 |
| }, |
| "SoccerTwos.Losses.BaselineLoss.sum": { |
| "value": 0.08009959459304809, |
| "min": 7.447628892502204e-06, |
| "max": 0.12023574585715929, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.LearningRate.mean": { |
| "value": 0.0003, |
| "min": 0.0003, |
| "max": 0.0003, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.LearningRate.sum": { |
| "value": 0.0003, |
| "min": 0.0003, |
| "max": 0.0003, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.Epsilon.mean": { |
| "value": 0.20000000000000007, |
| "min": 0.2, |
| "max": 0.20000000000000007, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.Epsilon.sum": { |
| "value": 0.20000000000000007, |
| "min": 0.2, |
| "max": 0.20000000000000007, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.Beta.mean": { |
| "value": 0.005000000000000001, |
| "min": 0.005, |
| "max": 0.005000000000000001, |
| "count": 2422 |
| }, |
| "SoccerTwos.Policy.Beta.sum": { |
| "value": 0.005000000000000001, |
| "min": 0.005, |
| "max": 0.005000000000000001, |
| "count": 2422 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1754278794", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/bolin/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": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.7.1+cu126", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1754337377" |
| }, |
| "total": 58583.416624648, |
| "count": 1, |
| "self": 0.1668565660074819, |
| "children": { |
| "run_training.setup": { |
| "total": 0.015344877000188717, |
| "count": 1, |
| "self": 0.015344877000188717 |
| }, |
| "TrainerController.start_learning": { |
| "total": 58583.234423204995, |
| "count": 1, |
| "self": 28.006689679357805, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.7130218009770033, |
| "count": 250, |
| "self": 3.7130218009770033 |
| }, |
| "TrainerController.advance": { |
| "total": 58551.44855011267, |
| "count": 3427750, |
| "self": 26.388956220180262, |
| "children": { |
| "env_step": { |
| "total": 23389.66532693994, |
| "count": 3427750, |
| "self": 19475.559716328786, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 3896.89595637029, |
| "count": 3427750, |
| "self": 182.23068291639538, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 3714.6652734538948, |
| "count": 6284314, |
| "self": 3714.6652734538948 |
| } |
| } |
| }, |
| "workers": { |
| "total": 17.20965424086353, |
| "count": 3427750, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 58544.79750145348, |
| "count": 3427750, |
| "is_parallel": true, |
| "self": 42551.46606135835, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0014544330001626804, |
| "count": 2, |
| "is_parallel": true, |
| "self": 0.00036373899956743116, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0010906940005952492, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0010906940005952492 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.012421765999988565, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003036180000890454, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0002772789998743974, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002772789998743974 |
| }, |
| "communicator.exchange": { |
| "total": 0.01087160400038556, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.01087160400038556 |
| }, |
| "steps_from_proto": { |
| "total": 0.000969264999639563, |
| "count": 2, |
| "is_parallel": true, |
| "self": 0.00022828999999546795, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0007409749996440951, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0007409749996440951 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 15993.118884885997, |
| "count": 3427749, |
| "is_parallel": true, |
| "self": 900.4193676668183, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 612.4480266295209, |
| "count": 3427749, |
| "is_parallel": true, |
| "self": 612.4480266295209 |
| }, |
| "communicator.exchange": { |
| "total": 11950.058678117999, |
| "count": 3427749, |
| "is_parallel": true, |
| "self": 11950.058678117999 |
| }, |
| "steps_from_proto": { |
| "total": 2530.1928124716583, |
| "count": 6855498, |
| "is_parallel": true, |
| "self": 435.93581838643513, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 2094.256994085223, |
| "count": 27421992, |
| "is_parallel": true, |
| "self": 2094.256994085223 |
| } |
| } |
| } |
| } |
| }, |
| "steps_from_proto": { |
| "total": 0.21255520914064618, |
| "count": 498, |
| "is_parallel": true, |
| "self": 0.03900427415192098, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.1735509349887252, |
| "count": 1992, |
| "is_parallel": true, |
| "self": 0.1735509349887252 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 35135.39426695255, |
| "count": 3427750, |
| "self": 266.1699697615768, |
| "children": { |
| "process_trajectory": { |
| "total": 5083.07728814891, |
| "count": 3427750, |
| "self": 5076.223328915879, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 6.853959233030309, |
| "count": 100, |
| "self": 6.853959233030309 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 29786.147009042066, |
| "count": 2422, |
| "self": 2878.9186776652605, |
| "children": { |
| "TorchPOCAOptimizer.update": { |
| "total": 26907.228331376806, |
| "count": 72672, |
| "self": 26907.228331376806 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 3.609966370277107e-07, |
| "count": 1, |
| "self": 3.609966370277107e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.06616125099390047, |
| "count": 1, |
| "self": 0.0009089379891520366, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.06525231300474843, |
| "count": 1, |
| "self": 0.06525231300474843 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
