{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.151453971862793, "min": 3.127227544784546, "max": 3.1760921478271484, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 64037.54296875, "min": 20419.759765625, "max": 111017.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 638.5, "min": 478.72727272727275, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20432.0, "min": 11828.0, "max": 27064.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1174.2121493977888, "min": 1165.2629482200864, "max": 1181.0289495804443, "count": 47 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9393.69719518231, "min": 2336.271198475225, "max": 16434.89980380847, "count": 47 }, "SoccerTwos.Step.mean": { "value": 2249936.0, "min": 1759929.0, "max": 2249936.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 2249936.0, "min": 1759929.0, "max": 2249936.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0031177180353552103, "min": -0.00878502894192934, "max": 0.0031177180353552103, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.049883488565683365, "min": -0.15813052654266357, "max": 0.049883488565683365, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.004119338467717171, "min": -0.008890403434634209, "max": 0.004119338467717171, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.06590941548347473, "min": -0.16002726554870605, "max": 0.06590941548347473, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0622749999165535, "min": -0.6666666666666666, "max": 0.2682857151542391, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.996399998664856, "min": -10.0, "max": 3.7560000121593475, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0622749999165535, "min": -0.6666666666666666, "max": 0.2682857151542391, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.996399998664856, "min": -10.0, "max": 3.7560000121593475, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014403438732309344, "min": 0.010229992038633402, "max": 0.019984069629572332, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014403438732309344, "min": 0.010229992038633402, "max": 0.019984069629572332, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003362401939618091, "min": 0.00013077333521020287, "max": 0.0043448854548235735, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003362401939618091, "min": 0.00013077333521020287, "max": 0.0043448854548235735, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0034127482950376967, "min": 0.00013574239558996246, "max": 0.0044469629181548955, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0034127482950376967, "min": 0.00013574239558996246, "max": 0.0044469629181548955, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005499999999999999, "min": 0.0005499999999999999, "max": 0.00055, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0005499999999999999, "min": 0.0005499999999999999, "max": 0.00055, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690804445", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690805540" }, "total": 1095.4753349929997, "count": 1, "self": 0.38822889600032795, "children": { "run_training.setup": { "total": 0.03129372500006866, "count": 1, "self": 0.03129372500006866 }, "TrainerController.start_learning": { "total": 1095.0558123719993, "count": 1, "self": 0.7822017468861304, "children": { "TrainerController._reset_env": { "total": 5.9570331720005925, "count": 4, "self": 5.9570331720005925 }, "TrainerController.advance": { "total": 1088.1120374991133, "count": 32835, "self": 0.8069334171414084, "children": { "env_step": { "total": 882.2106680920333, "count": 32835, "self": 699.2274848741445, "children": { "SubprocessEnvManager._take_step": { "total": 182.54068637993714, "count": 32835, "self": 5.318234501108236, "children": { "TorchPolicy.evaluate": { "total": 177.2224518788289, "count": 65094, "self": 177.2224518788289 } } }, "workers": { "total": 0.44249683795169403, "count": 32835, "self": 0.0, "children": { "worker_root": { "total": 1092.3884063230407, "count": 32835, "is_parallel": true, "self": 498.6851029291065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00451230700036831, "count": 2, "is_parallel": true, "self": 0.0009606280018488178, "children": { "_process_rank_one_or_two_observation": { "total": 0.003551678998519492, "count": 8, "is_parallel": true, "self": 0.003551678998519492 } } }, "UnityEnvironment.step": { "total": 0.07229993299915805, "count": 1, "is_parallel": true, "self": 0.001307245998759754, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007551199996669311, "count": 1, "is_parallel": true, "self": 0.0007551199996669311 }, "communicator.exchange": { "total": 0.06639388900021004, "count": 1, "is_parallel": true, "self": 0.06639388900021004 }, "steps_from_proto": { "total": 0.0038436780005213222, "count": 2, "is_parallel": true, "self": 0.0006122100003267406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032314680001945817, "count": 8, "is_parallel": true, "self": 0.0032314680001945817 } } } } } } }, "steps_from_proto": { "total": 0.007196964998911426, "count": 6, "is_parallel": true, "self": 0.0013209269991421024, "children": { "_process_rank_one_or_two_observation": { "total": 0.0058760379997693235, "count": 24, "is_parallel": true, "self": 0.0058760379997693235 } } }, "UnityEnvironment.step": { "total": 593.6961064289353, "count": 32834, "is_parallel": true, "self": 36.63282161472853, "children": { "UnityEnvironment._generate_step_input": { "total": 23.15455671015843, "count": 32834, "is_parallel": true, "self": 23.15455671015843 }, "communicator.exchange": { "total": 416.26482188099453, "count": 32834, "is_parallel": true, "self": 416.26482188099453 }, "steps_from_proto": { "total": 117.64390622305382, "count": 65668, "is_parallel": true, "self": 19.087857136731145, "children": { "_process_rank_one_or_two_observation": { "total": 98.55604908632267, "count": 262672, "is_parallel": true, "self": 98.55604908632267 } } } } } } } } } } }, "trainer_advance": { "total": 205.09443598993857, "count": 32835, "self": 6.719612829871949, "children": { "process_trajectory": { "total": 50.66163941806735, "count": 32835, "self": 50.458558852067654, "children": { "RLTrainer._checkpoint": { "total": 0.2030805659996986, "count": 1, "self": 0.2030805659996986 } } }, "_update_policy": { "total": 147.71318374199927, "count": 23, "self": 103.30691072398713, "children": { "TorchPOCAOptimizer.update": { "total": 44.40627301801214, "count": 693, "self": 44.40627301801214 } } } } } } }, "trainer_threads": { "total": 9.93999492493458e-07, "count": 1, "self": 9.93999492493458e-07 }, "TrainerController._save_models": { "total": 0.20453895999980887, "count": 1, "self": 0.0014291139996203128, "children": { "RLTrainer._checkpoint": { "total": 0.20310984600018855, "count": 1, "self": 0.20310984600018855 } } } } } } }