{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7445931434631348, "min": 1.6850866079330444, "max": 3.2957451343536377, "count": 563 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34724.3828125, "min": 10711.3671875, "max": 105463.84375, "count": 563 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.542857142857144, "min": 37.18939393939394, "max": 861.1111111111111, "count": 563 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19548.0, "min": 8200.0, "max": 31000.0, "count": 563 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1572.6787625822285, "min": 1187.8306343789218, "max": 1572.6787625822285, "count": 563 }, "SoccerTwos.Self-play.ELO.sum": { "value": 330262.540142268, "min": 4761.159386812556, "max": 388381.16085913655, "count": 563 }, "SoccerTwos.Step.mean": { "value": 5629965.0, "min": 9686.0, "max": 5629965.0, "count": 563 }, "SoccerTwos.Step.sum": { "value": 5629965.0, "min": 9686.0, "max": 5629965.0, "count": 563 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01401924155652523, "min": -0.10446890443563461, "max": 0.21584397554397583, "count": 563 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.9440407752990723, "min": -20.67490005493164, "max": 33.303619384765625, "count": 563 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014381909742951393, "min": -0.10639803111553192, "max": 0.21651381254196167, "count": 563 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.0202009677886963, "min": -21.695873260498047, "max": 36.781734466552734, "count": 563 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 563 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 563 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.011637141874858311, "min": -0.6318666656812032, "max": 0.4154938047966071, "count": 563 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.4437997937202454, "min": -55.973999977111816, "max": 57.87480020523071, "count": 563 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.011637141874858311, "min": -0.6318666656812032, "max": 0.4154938047966071, "count": 563 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.4437997937202454, "min": -55.973999977111816, "max": 57.87480020523071, "count": 563 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 563 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 563 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01681263987751057, "min": 0.009970807051286102, "max": 0.023588940827175976, "count": 271 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01681263987751057, "min": 0.009970807051286102, "max": 0.023588940827175976, "count": 271 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12133442386984825, "min": 0.0036122541014964762, "max": 0.13310990159710248, "count": 271 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12133442386984825, "min": 0.0036122541014964762, "max": 0.13310990159710248, "count": 271 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12454693143566449, "min": 0.003364604473925936, "max": 0.13591177513202032, "count": 271 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12454693143566449, "min": 0.003364604473925936, "max": 0.13591177513202032, "count": 271 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 271 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 271 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 271 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 271 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 271 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 271 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675496201", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/aj/anaconda3/envs/rl/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./SoccerTwos.x86_64 --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": "1.13.1+cu117", "numpy_version": "1.21.0", "end_time_seconds": "1675501882" }, "total": 5681.631443330001, "count": 1, "self": 0.36721379100163176, "children": { "run_training.setup": { "total": 0.009893450000163284, "count": 1, "self": 0.009893450000163284 }, "TrainerController.start_learning": { "total": 5681.2543360889995, "count": 1, "self": 6.013943085377832, "children": { "TrainerController._reset_env": { "total": 1.6326506650002557, "count": 29, "self": 1.6326506650002557 }, "TrainerController.advance": { "total": 5673.5077513796205, "count": 391656, "self": 5.791406961161556, "children": { "env_step": { "total": 4129.888640451547, "count": 391656, "self": 2977.331019370007, "children": { "SubprocessEnvManager._take_step": { "total": 1149.2225142639873, "count": 391656, "self": 29.32610332744298, "children": { "TorchPolicy.evaluate": { "total": 1119.8964109365443, "count": 708938, "self": 1119.8964109365443 } } }, "workers": { "total": 3.3351068175525143, "count": 391656, "self": 0.0, "children": { "worker_root": { "total": 5672.611461594681, "count": 391656, "is_parallel": true, "self": 3284.0772732661026, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014479720011877362, "count": 2, "is_parallel": true, "self": 0.0003768440037674736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010711279974202625, "count": 8, "is_parallel": true, "self": 0.0010711279974202625 } } }, "UnityEnvironment.step": { "total": 0.015645661000235123, "count": 1, "is_parallel": true, "self": 0.00038880300053278916, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029232899942144286, "count": 1, "is_parallel": true, "self": 0.00029232899942144286 }, "communicator.exchange": { "total": 0.013842027999999118, "count": 1, "is_parallel": true, "self": 0.013842027999999118 }, "steps_from_proto": { "total": 0.0011225010002817726, "count": 2, "is_parallel": true, "self": 0.00025512100182822905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008673799984535435, "count": 8, "is_parallel": true, "self": 0.0008673799984535435 } } } } } } }, "UnityEnvironment.step": { "total": 2388.50238450858, "count": 391655, "is_parallel": true, "self": 143.95996350808855, "children": { "UnityEnvironment._generate_step_input": { "total": 94.35225239944884, "count": 391655, "is_parallel": true, "self": 94.35225239944884 }, "communicator.exchange": { "total": 1740.7283542312416, "count": 391655, "is_parallel": true, "self": 1740.7283542312416 }, "steps_from_proto": { "total": 409.4618143698008, "count": 783310, "is_parallel": true, "self": 90.78960065160027, "children": { "_process_rank_one_or_two_observation": { "total": 318.6722137182005, "count": 3133240, "is_parallel": true, "self": 318.6722137182005 } } } } }, "steps_from_proto": { "total": 0.031803819998458494, "count": 56, "is_parallel": true, "self": 0.007017880976491142, "children": { "_process_rank_one_or_two_observation": { "total": 0.02478593902196735, "count": 224, "is_parallel": true, "self": 0.02478593902196735 } } } } } } } } }, "trainer_advance": { "total": 1537.827703966912, "count": 391656, "self": 36.89562855519216, "children": { "process_trajectory": { "total": 681.1944579387109, "count": 391656, "self": 680.1112748497108, "children": { "RLTrainer._checkpoint": { "total": 1.0831830890001584, "count": 11, "self": 1.0831830890001584 } } }, "_update_policy": { "total": 819.7376174730089, "count": 272, "self": 533.5363305260798, "children": { "TorchPOCAOptimizer.update": { "total": 286.20128694692903, "count": 8149, "self": 286.20128694692903 } } } } } } }, "trainer_threads": { "total": 1.3709995982935652e-06, "count": 1, "self": 1.3709995982935652e-06 }, "TrainerController._save_models": { "total": 0.0999895880013355, "count": 1, "self": 0.0008468070009257644, "children": { "RLTrainer._checkpoint": { "total": 0.09914278100040974, "count": 1, "self": 0.09914278100040974 } } } } } } }