{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4839317798614502, "min": 1.3217110633850098, "max": 3.295750617980957, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31008.23828125, "min": 12233.826171875, "max": 139907.46875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.43661971830986, "min": 40.63025210084034, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20004.0, "min": 11988.0, "max": 29272.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1663.774809225339, "min": 1194.156890251674, "max": 1700.1999188622788, "count": 4811 }, "SoccerTwos.Self-play.ELO.sum": { "value": 236256.02290999814, "min": 2388.3137805033484, "max": 354933.7148393992, "count": 4811 }, "SoccerTwos.Step.mean": { "value": 49999826.0, "min": 9096.0, "max": 49999826.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999826.0, "min": 9096.0, "max": 49999826.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03001251630485058, "min": -0.17046482861042023, "max": 0.16957390308380127, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.231764793395996, "min": -29.149484634399414, "max": 31.92991828918457, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03009491041302681, "min": -0.17105722427368164, "max": 0.17510975897312164, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.243382453918457, "min": -29.25078582763672, "max": 32.16276550292969, "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": -0.06979858198909895, "min": -0.631578947368421, "max": 0.4511478284130926, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.841600060462952, "min": -62.49959981441498, "max": 65.8615996837616, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06979858198909895, "min": -0.631578947368421, "max": 0.4511478284130926, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.841600060462952, "min": -62.49959981441498, "max": 65.8615996837616, "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": 0.014501520027321628, "min": 0.009576276894222246, "max": 0.02516175553901121, "count": 2413 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014501520027321628, "min": 0.009576276894222246, "max": 0.02516175553901121, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08913260574142139, "min": 1.6679876887100893e-08, "max": 0.12145498543977737, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08913260574142139, "min": 1.6679876887100893e-08, "max": 0.12145498543977737, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09005878468354543, "min": 1.8300759988913264e-08, "max": 0.12307501683632532, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09005878468354543, "min": 1.8300759988913264e-08, "max": 0.12307501683632532, "count": 2413 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712088591", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/hui/conda/anaconda3/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": "1.1.0.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": "1712426607" }, "total": 338016.229729331, "count": 1, "self": 10.26993561803829, "children": { "run_training.setup": { "total": 0.029621077002957463, "count": 1, "self": 0.029621077002957463 }, "TrainerController.start_learning": { "total": 338005.93017263594, "count": 1, "self": 94.73738962272182, "children": { "TrainerController._reset_env": { "total": 13.276130230748095, "count": 209, "self": 13.276130230748095 }, "TrainerController.advance": { "total": 337897.2613632415, "count": 3408035, "self": 106.42749221005943, "children": { "env_step": { "total": 81938.0193208165, "count": 3408035, "self": 65020.16224968282, "children": { "SubprocessEnvManager._take_step": { "total": 16859.248587368988, "count": 3408035, "self": 696.1393022305565, "children": { "TorchPolicy.evaluate": { "total": 16163.109285138431, "count": 6289310, "self": 16163.109285138431 } } }, "workers": { "total": 58.60848376469221, "count": 3408035, "self": 0.0, "children": { "worker_root": { "total": 337841.55069500406, "count": 3408035, "is_parallel": true, "self": 284218.66538325825, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.026187706971541047, "count": 2, "is_parallel": true, "self": 0.023293153033591807, "children": { "_process_rank_one_or_two_observation": { "total": 0.00289455393794924, "count": 8, "is_parallel": true, "self": 0.00289455393794924 } } }, "UnityEnvironment.step": { "total": 0.05771382397506386, "count": 1, "is_parallel": true, "self": 0.0008700748439878225, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0031269040191546082, "count": 1, "is_parallel": true, "self": 0.0031269040191546082 }, "communicator.exchange": { "total": 0.05170545005239546, "count": 1, "is_parallel": true, "self": 0.05170545005239546 }, "steps_from_proto": { "total": 0.0020113950595259666, "count": 2, "is_parallel": true, "self": 0.0004623152781277895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015490797813981771, "count": 8, "is_parallel": true, "self": 0.0015490797813981771 } } } } } } }, "UnityEnvironment.step": { "total": 53622.37083138793, "count": 3408034, "is_parallel": true, "self": 3348.1403495456325, "children": { "UnityEnvironment._generate_step_input": { "total": 2346.449156976538, "count": 3408034, "is_parallel": true, "self": 2346.449156976538 }, "communicator.exchange": { "total": 38363.26626932307, "count": 3408034, "is_parallel": true, "self": 38363.26626932307 }, "steps_from_proto": { "total": 9564.515055542695, "count": 6816068, "is_parallel": true, "self": 1834.4778924479615, "children": { "_process_rank_one_or_two_observation": { "total": 7730.037163094734, "count": 27264272, "is_parallel": true, "self": 7730.037163094734 } } } } }, "steps_from_proto": { "total": 0.5144803578732535, "count": 416, "is_parallel": true, "self": 0.09764499438460916, "children": { "_process_rank_one_or_two_observation": { "total": 0.41683536348864436, "count": 1664, "is_parallel": true, "self": 0.41683536348864436 } } } } } } } } }, "trainer_advance": { "total": 255852.8145502149, "count": 3408035, "self": 715.5272634963039, "children": { "process_trajectory": { "total": 20634.581765327603, "count": 3408035, "self": 20585.784304664936, "children": { "RLTrainer._checkpoint": { "total": 48.79746066266671, "count": 100, "self": 48.79746066266671 } } }, "_update_policy": { "total": 234502.705521391, "count": 2413, "self": 8308.750875544036, "children": { "TorchPOCAOptimizer.update": { "total": 226193.95464584697, "count": 72402, "self": 226193.95464584697 } } } } } } }, "trainer_threads": { "total": 1.210952177643776e-06, "count": 1, "self": 1.210952177643776e-06 }, "TrainerController._save_models": { "total": 0.65528833004646, "count": 1, "self": 0.11293255211785436, "children": { "RLTrainer._checkpoint": { "total": 0.5423557779286057, "count": 1, "self": 0.5423557779286057 } } } } } } }