{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7002947330474854, "min": 1.6380585432052612, "max": 3.295743465423584, "count": 1425 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33080.93359375, "min": 17482.62109375, "max": 137784.5625, "count": 1425 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.308510638297875, "min": 37.49612403100775, "max": 999.0, "count": 1425 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19668.0, "min": 16300.0, "max": 23604.0, "count": 1425 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1515.8465361246608, "min": 1175.8420184870574, "max": 1547.5825357088704, "count": 1414 }, "SoccerTwos.Self-play.ELO.sum": { "value": 284979.1487914362, "min": 2353.0056904809553, "max": 385852.05604644405, "count": 1414 }, "SoccerTwos.Step.mean": { "value": 14249978.0, "min": 9344.0, "max": 14249978.0, "count": 1425 }, "SoccerTwos.Step.sum": { "value": 14249978.0, "min": 9344.0, "max": 14249978.0, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05131640285253525, "min": -0.13127030432224274, "max": 0.19487570226192474, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.698800086975098, "min": -25.728979110717773, "max": 29.815982818603516, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05251322314143181, "min": -0.1329604685306549, "max": 0.20376066863536835, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.924999237060547, "min": -26.060253143310547, "max": 31.175382614135742, "count": 1425 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1425 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1327322759325542, "min": -0.6153846153846154, "max": 0.4017777707841661, "count": 1425 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.086400151252747, "min": -73.89079988002777, "max": 59.281800270080566, "count": 1425 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1327322759325542, "min": -0.6153846153846154, "max": 0.4017777707841661, "count": 1425 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.086400151252747, "min": -73.89079988002777, "max": 59.281800270080566, "count": 1425 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1425 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1425 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015123945882078261, "min": 0.009782215244194958, "max": 0.02437352481453369, "count": 688 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015123945882078261, "min": 0.009782215244194958, "max": 0.02437352481453369, "count": 688 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11028323496381441, "min": 0.000451071868398382, "max": 0.13022388244668642, "count": 688 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11028323496381441, "min": 0.000451071868398382, "max": 0.13022388244668642, "count": 688 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11236175894737244, "min": 0.00045222041468756893, "max": 0.13352629070480665, "count": 688 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11236175894737244, "min": 0.00045222041468756893, "max": 0.13352629070480665, "count": 688 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 688 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 688 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 688 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 688 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 688 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 688 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731604935", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/home/pixel/.local/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1731626327" }, "total": 21392.081185383002, "count": 1, "self": 0.1749876310059335, "children": { "run_training.setup": { "total": 0.010573133997240802, "count": 1, "self": 0.010573133997240802 }, "TrainerController.start_learning": { "total": 21391.895624618, "count": 1, "self": 8.937597158987046, "children": { "TrainerController._reset_env": { "total": 2.373008899987326, "count": 72, "self": 2.373008899987326 }, "TrainerController.advance": { "total": 21380.435102241026, "count": 981749, "self": 9.277294615323626, "children": { "env_step": { "total": 16587.329403388267, "count": 981749, "self": 8943.572544190898, "children": { "SubprocessEnvManager._take_step": { "total": 7637.971230250809, "count": 981749, "self": 67.06691184024749, "children": { "TorchPolicy.evaluate": { "total": 7570.904318410561, "count": 1797235, "self": 7570.904318410561 } } }, "workers": { "total": 5.785628946559882, "count": 981748, "self": 0.0, "children": { "worker_root": { "total": 21370.996351611477, "count": 981748, "is_parallel": true, "self": 13540.540777570408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019749860002775677, "count": 2, "is_parallel": true, "self": 0.0006615740021516103, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013134119981259573, "count": 8, "is_parallel": true, "self": 0.0013134119981259573 } } }, "UnityEnvironment.step": { "total": 0.01724394399934681, "count": 1, "is_parallel": true, "self": 0.00031886899887467735, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030207699819584377, "count": 1, "is_parallel": true, "self": 0.00030207699819584377 }, "communicator.exchange": { "total": 0.015609043999575078, "count": 1, "is_parallel": true, "self": 0.015609043999575078 }, "steps_from_proto": { "total": 0.0010139540027012117, "count": 2, "is_parallel": true, "self": 0.0002164349971280899, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007975190055731218, "count": 8, "is_parallel": true, "self": 0.0007975190055731218 } } } } } } }, "UnityEnvironment.step": { "total": 7830.383839585051, "count": 981747, "is_parallel": true, "self": 276.4501628534017, "children": { "UnityEnvironment._generate_step_input": { "total": 171.5936123928368, "count": 981747, "is_parallel": true, "self": 171.5936123928368 }, "communicator.exchange": { "total": 6520.458626116433, "count": 981747, "is_parallel": true, "self": 6520.458626116433 }, "steps_from_proto": { "total": 861.8814382223791, "count": 1963494, "is_parallel": true, "self": 161.40831380626696, "children": { "_process_rank_one_or_two_observation": { "total": 700.4731244161121, "count": 7853976, "is_parallel": true, "self": 700.4731244161121 } } } } }, "steps_from_proto": { "total": 0.07173445601802086, "count": 142, "is_parallel": true, "self": 0.013971495136502199, "children": { "_process_rank_one_or_two_observation": { "total": 0.057762960881518666, "count": 568, "is_parallel": true, "self": 0.057762960881518666 } } } } } } } } }, "trainer_advance": { "total": 4783.828404237436, "count": 981748, "self": 75.53843808118836, "children": { "process_trajectory": { "total": 2881.9490059952404, "count": 981748, "self": 2877.8293614802315, "children": { "RLTrainer._checkpoint": { "total": 4.119644515008986, "count": 28, "self": 4.119644515008986 } } }, "_update_policy": { "total": 1826.3409601610074, "count": 688, "self": 875.0133993380223, "children": { "TorchPOCAOptimizer.update": { "total": 951.3275608229851, "count": 20640, "self": 951.3275608229851 } } } } } } }, "trainer_threads": { "total": 7.399939931929111e-07, "count": 1, "self": 7.399939931929111e-07 }, "TrainerController._save_models": { "total": 0.14991557800385635, "count": 1, "self": 0.0017659920049482025, "children": { "RLTrainer._checkpoint": { "total": 0.14814958599890815, "count": 1, "self": 0.14814958599890815 } } } } } } }