{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8181488513946533, "min": 1.7722526788711548, "max": 3.2956998348236084, "count": 659 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37584.7734375, "min": 29269.234375, "max": 145997.671875, "count": 659 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.56122448979592, "min": 39.512, "max": 999.0, "count": 659 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20212.0, "min": 16148.0, "max": 24588.0, "count": 659 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1625.6385262762049, "min": 1197.8567062005566, "max": 1668.2787321967437, "count": 649 }, "SoccerTwos.Self-play.ELO.sum": { "value": 318625.15115013614, "min": 2396.098789849506, "max": 402718.1052663548, "count": 649 }, "SoccerTwos.Step.mean": { "value": 6589980.0, "min": 9316.0, "max": 6589980.0, "count": 659 }, "SoccerTwos.Step.sum": { "value": 6589980.0, "min": 9316.0, "max": 6589980.0, "count": 659 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0475546196103096, "min": -0.09808246046304703, "max": 0.21291950345039368, "count": 659 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.32070541381836, "min": -18.76749038696289, "max": 29.973407745361328, "count": 659 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04745898023247719, "min": -0.09845352172851562, "max": 0.21285639703273773, "count": 659 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.301959991455078, "min": -18.61127281188965, "max": 29.77692985534668, "count": 659 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 659 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 659 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06421632669409927, "min": -0.6153846153846154, "max": 0.5872666626064865, "count": 659 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -12.586400032043457, "min": -68.12359976768494, "max": 63.42479956150055, "count": 659 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06421632669409927, "min": -0.6153846153846154, "max": 0.5872666626064865, "count": 659 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -12.586400032043457, "min": -68.12359976768494, "max": 63.42479956150055, "count": 659 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 659 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 659 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017225077951540393, "min": 0.010249892457310731, "max": 0.022830745864969988, "count": 317 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017225077951540393, "min": 0.010249892457310731, "max": 0.022830745864969988, "count": 317 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1198251726726691, "min": 3.381514870852698e-05, "max": 0.1250131058196227, "count": 317 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1198251726726691, "min": 3.381514870852698e-05, "max": 0.1250131058196227, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12238212376832962, "min": 3.8423656284673295e-05, "max": 0.1284385047852993, "count": 317 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12238212376832962, "min": 3.8423656284673295e-05, "max": 0.1284385047852993, "count": 317 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 317 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 317 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 317 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 317 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 317 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 317 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713892128", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/rl/bin/mlagents-learn --base-port=8123 ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --resume --no-graphics", "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": "1713931655" }, "total": 39527.12577596097, "count": 1, "self": 0.4958153588231653, "children": { "run_training.setup": { "total": 0.14485983410850167, "count": 1, "self": 0.14485983410850167 }, "TrainerController.start_learning": { "total": 39526.48510076804, "count": 1, "self": 20.37506204028614, "children": { "TrainerController._reset_env": { "total": 4.309405425796285, "count": 33, "self": 4.309405425796285 }, "TrainerController.advance": { "total": 39501.54427919118, "count": 452563, "self": 20.517467162804678, "children": { "env_step": { "total": 13579.198964179726, "count": 452563, "self": 10257.335112611298, "children": { "SubprocessEnvManager._take_step": { "total": 3309.22183962306, "count": 452563, "self": 123.12322941585444, "children": { "TorchPolicy.evaluate": { "total": 3186.0986102072056, "count": 831486, "self": 3186.0986102072056 } } }, "workers": { "total": 12.642011945368722, "count": 452563, "self": 0.0, "children": { "worker_root": { "total": 39458.70679526264, "count": 452563, "is_parallel": true, "self": 31481.193910411792, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005868686828762293, "count": 2, "is_parallel": true, "self": 0.0013330031652003527, "children": { "_process_rank_one_or_two_observation": { "total": 0.00453568366356194, "count": 8, "is_parallel": true, "self": 0.00453568366356194 } } }, "UnityEnvironment.step": { "total": 0.05623332806862891, "count": 1, "is_parallel": true, "self": 0.0019329320639371872, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0014684719499200583, "count": 1, "is_parallel": true, "self": 0.0014684719499200583 }, "communicator.exchange": { "total": 0.04584660101681948, "count": 1, "is_parallel": true, "self": 0.04584660101681948 }, "steps_from_proto": { "total": 0.006985323037952185, "count": 2, "is_parallel": true, "self": 0.0013418199960142374, "children": { "_process_rank_one_or_two_observation": { "total": 0.005643503041937947, "count": 8, "is_parallel": true, "self": 0.005643503041937947 } } } } } } }, "UnityEnvironment.step": { "total": 7977.407115461305, "count": 452562, "is_parallel": true, "self": 449.1514831224922, "children": { "UnityEnvironment._generate_step_input": { "total": 334.9367151935585, "count": 452562, "is_parallel": true, "self": 334.9367151935585 }, "communicator.exchange": { "total": 5785.861816139426, "count": 452562, "is_parallel": true, "self": 5785.861816139426 }, "steps_from_proto": { "total": 1407.457101005828, "count": 905124, "is_parallel": true, "self": 289.18100964301266, "children": { "_process_rank_one_or_two_observation": { "total": 1118.2760913628154, "count": 3620496, "is_parallel": true, "self": 1118.2760913628154 } } } } }, "steps_from_proto": { "total": 0.10576938954181969, "count": 64, "is_parallel": true, "self": 0.022471004398539662, "children": { "_process_rank_one_or_two_observation": { "total": 0.08329838514328003, "count": 256, "is_parallel": true, "self": 0.08329838514328003 } } } } } } } } }, "trainer_advance": { "total": 25901.827847848646, "count": 452563, "self": 163.48539146594703, "children": { "process_trajectory": { "total": 4067.924119583098, "count": 452563, "self": 4064.3509987569414, "children": { "RLTrainer._checkpoint": { "total": 3.57312082615681, "count": 13, "self": 3.57312082615681 } } }, "_update_policy": { "total": 21670.4183367996, "count": 318, "self": 1565.2620773571543, "children": { "TorchPOCAOptimizer.update": { "total": 20105.156259442447, "count": 9523, "self": 20105.156259442447 } } } } } } }, "trainer_threads": { "total": 1.5599653124809265e-06, "count": 1, "self": 1.5599653124809265e-06 }, "TrainerController._save_models": { "total": 0.2563525508157909, "count": 1, "self": 0.005667787743732333, "children": { "RLTrainer._checkpoint": { "total": 0.25068476307205856, "count": 1, "self": 0.25068476307205856 } } } } } } }