{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3642840385437012, "min": 1.3309460878372192, "max": 3.2957050800323486, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28333.451171875, "min": 18824.236328125, "max": 134818.796875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.42857142857143, "min": 38.685483870967744, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19536.0, "min": 11764.0, "max": 29004.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1476.7826459204307, "min": 1187.359195178111, "max": 1609.0609483598403, "count": 4998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 227424.52747174632, "min": 2377.455822252568, "max": 378674.29368815693, "count": 4998 }, "SoccerTwos.Step.mean": { "value": 49999948.0, "min": 9518.0, "max": 49999948.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999948.0, "min": 9518.0, "max": 49999948.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03670903667807579, "min": -0.14049525558948517, "max": 0.17864368855953217, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.653191566467285, "min": -27.11031150817871, "max": 27.32752227783203, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03587992489337921, "min": -0.13726955652236938, "max": 0.18451468646526337, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.525508403778076, "min": -26.060300827026367, "max": 26.73061752319336, "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": -0.004228573340874214, "min": -0.5333333333333333, "max": 0.5204064557629247, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.6512002944946289, "min": -69.33999991416931, "max": 70.19380009174347, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.004228573340874214, "min": -0.5333333333333333, "max": 0.5204064557629247, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.6512002944946289, "min": -69.33999991416931, "max": 70.19380009174347, "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": 0.012472246635782842, "min": 0.010156642621101735, "max": 0.025759396608918905, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012472246635782842, "min": 0.010156642621101735, "max": 0.025759396608918905, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09122076332569122, "min": 0.0007721815035135175, "max": 0.12964768807093302, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09122076332569122, "min": 0.0007721815035135175, "max": 0.12964768807093302, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09219344134132067, "min": 0.0007724896888248623, "max": 0.1322729304432869, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09219344134132067, "min": 0.0007724896888248623, "max": 0.1322729304432869, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712459075", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/jinghuan/.conda/envs/rl_py10/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712645118" }, "total": 186042.95730458386, "count": 1, "self": 0.42164613492786884, "children": { "run_training.setup": { "total": 0.014359293971210718, "count": 1, "self": 0.014359293971210718 }, "TrainerController.start_learning": { "total": 186042.52129915496, "count": 1, "self": 43.02053129579872, "children": { "TrainerController._reset_env": { "total": 9.091848194599152, "count": 250, "self": 9.091848194599152 }, "TrainerController.advance": { "total": 185990.2364280154, "count": 3453061, "self": 43.05949105974287, "children": { "env_step": { "total": 160152.17570470786, "count": 3453061, "self": 97256.45733426698, "children": { "SubprocessEnvManager._take_step": { "total": 62870.10368987499, "count": 3453061, "self": 324.4425852135755, "children": { "TorchPolicy.evaluate": { "total": 62545.66110466141, "count": 6278462, "self": 62545.66110466141 } } }, "workers": { "total": 25.61468056589365, "count": 3453061, "self": 0.0, "children": { "worker_root": { "total": 185748.17667129915, "count": 3453061, "is_parallel": true, "self": 97101.17736303573, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006627525668591261, "count": 2, "is_parallel": true, "self": 0.0015474511310458183, "children": { "_process_rank_one_or_two_observation": { "total": 0.005080074537545443, "count": 8, "is_parallel": true, "self": 0.005080074537545443 } } }, "UnityEnvironment.step": { "total": 0.047877667006105185, "count": 1, "is_parallel": true, "self": 0.001653832383453846, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012996373698115349, "count": 1, "is_parallel": true, "self": 0.0012996373698115349 }, "communicator.exchange": { "total": 0.040173609275370836, "count": 1, "is_parallel": true, "self": 0.040173609275370836 }, "steps_from_proto": { "total": 0.0047505879774689674, "count": 2, "is_parallel": true, "self": 0.0009069270454347134, "children": { "_process_rank_one_or_two_observation": { "total": 0.003843660932034254, "count": 8, "is_parallel": true, "self": 0.003843660932034254 } } } } } } }, "UnityEnvironment.step": { "total": 88645.84682184411, "count": 3453060, "is_parallel": true, "self": 5246.0012119724415, "children": { "UnityEnvironment._generate_step_input": { "total": 3738.271375231445, "count": 3453060, "is_parallel": true, "self": 3738.271375231445 }, "communicator.exchange": { "total": 64786.52102768235, "count": 3453060, "is_parallel": true, "self": 64786.52102768235 }, "steps_from_proto": { "total": 14875.053206957877, "count": 6906120, "is_parallel": true, "self": 2806.225925695151, "children": { "_process_rank_one_or_two_observation": { "total": 12068.827281262726, "count": 27624480, "is_parallel": true, "self": 12068.827281262726 } } } } }, "steps_from_proto": { "total": 1.1524864193052053, "count": 498, "is_parallel": true, "self": 0.2139191417954862, "children": { "_process_rank_one_or_two_observation": { "total": 0.9385672775097191, "count": 1992, "is_parallel": true, "self": 0.9385672775097191 } } } } } } } } }, "trainer_advance": { "total": 25795.0012322478, "count": 3453061, "self": 306.4589294404723, "children": { "process_trajectory": { "total": 16522.97932873806, "count": 3453061, "self": 16501.552819521632, "children": { "RLTrainer._checkpoint": { "total": 21.426509216427803, "count": 100, "self": 21.426509216427803 } } }, "_update_policy": { "total": 8965.562974069268, "count": 2425, "self": 4947.9246844635345, "children": { "TorchPOCAOptimizer.update": { "total": 4017.638289605733, "count": 72753, "self": 4017.638289605733 } } } } } } }, "trainer_threads": { "total": 9.201467037200928e-07, "count": 1, "self": 9.201467037200928e-07 }, "TrainerController._save_models": { "total": 0.17249072901904583, "count": 1, "self": 0.001132055651396513, "children": { "RLTrainer._checkpoint": { "total": 0.17135867336764932, "count": 1, "self": 0.17135867336764932 } } } } } } }