{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.107206344604492, "min": 3.0534372329711914, "max": 3.2957544326782227, "count": 333 }, "SoccerTwos.Policy.Entropy.sum": { "value": 74771.8125, "min": 4622.4150390625, "max": 124757.15625, "count": 333 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 441.0, "max": 999.0, "count": 333 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 1764.0, "max": 30312.0, "count": 333 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1189.0831169313972, "min": 1186.4567907865392, "max": 1204.1695622204547, "count": 214 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4756.332467725589, "min": 2372.9135815730783, "max": 14379.462461201445, "count": 214 }, "SoccerTwos.Step.mean": { "value": 3329570.0, "min": 9196.0, "max": 3329570.0, "count": 333 }, "SoccerTwos.Step.sum": { "value": 3329570.0, "min": 9196.0, "max": 3329570.0, "count": 333 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.051005177199840546, "min": -0.07919275015592575, "max": 0.07981809973716736, "count": 333 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5100517868995667, "min": -0.871120274066925, "max": 1.192604660987854, "count": 333 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08291853964328766, "min": -0.08291853964328766, "max": 0.05548698827624321, "count": 333 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.829185426235199, "min": -1.064375877380371, "max": 0.8207140564918518, "count": 333 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 333 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 333 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5454545454545454, "max": 0.31094286271503996, "count": 333 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.0, "max": 4.353200078010559, "count": 333 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5454545454545454, "max": 0.31094286271503996, "count": 333 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.0, "max": 4.353200078010559, "count": 333 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 333 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019722058397686246, "min": 0.009528054924642978, "max": 0.02253799793931345, "count": 154 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019722058397686246, "min": 0.009528054924642978, "max": 0.02253799793931345, "count": 154 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0038427712531605113, "min": 2.1490599664275578e-07, "max": 2.628205533968867, "count": 154 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0038427712531605113, "min": 2.1490599664275578e-07, "max": 2.628205533968867, "count": 154 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.020994603575672954, "min": 2.9414611238583653e-07, "max": 0.2821526768888968, "count": 154 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.020994603575672954, "min": 2.9414611238583653e-07, "max": 0.2821526768888968, "count": 154 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0009900000000000002, "min": 0.0009899999999999998, "max": 0.0009900000000000002, "count": 154 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0009900000000000002, "min": 0.0009899999999999998, "max": 0.0009900000000000002, "count": 154 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 154 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 154 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 154 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 154 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691826076", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "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": "1691833292" }, "total": 7216.5758620199995, "count": 1, "self": 0.009842163998655451, "children": { "run_training.setup": { "total": 0.04366558400010945, "count": 1, "self": 0.04366558400010945 }, "TrainerController.start_learning": { "total": 7216.5223542720005, "count": 1, "self": 4.975681062150215, "children": { "TrainerController._reset_env": { "total": 6.7716828349989555, "count": 17, "self": 6.7716828349989555 }, "TrainerController.advance": { "total": 7204.075525104852, "count": 217140, "self": 5.224346830639661, "children": { "env_step": { "total": 5748.202097241937, "count": 217140, "self": 4564.009883959964, "children": { "SubprocessEnvManager._take_step": { "total": 1181.1519834882147, "count": 217140, "self": 37.85409066504508, "children": { "TorchPolicy.evaluate": { "total": 1143.2978928231696, "count": 431106, "self": 1143.2978928231696 } } }, "workers": { "total": 3.0402297937582716, "count": 217140, "self": 0.0, "children": { "worker_root": { "total": 7197.866463875, "count": 217140, "is_parallel": true, "self": 3335.6854850021064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007193444999984422, "count": 2, "is_parallel": true, "self": 0.0048797159995501715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023137290004342503, "count": 8, "is_parallel": true, "self": 0.0023137290004342503 } } }, "UnityEnvironment.step": { "total": 0.08231228299996474, "count": 1, "is_parallel": true, "self": 0.0013464339999700314, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008666799999446084, "count": 1, "is_parallel": true, "self": 0.0008666799999446084 }, "communicator.exchange": { "total": 0.07573204699997405, "count": 1, "is_parallel": true, "self": 0.07573204699997405 }, "steps_from_proto": { "total": 0.004367122000076051, "count": 2, "is_parallel": true, "self": 0.0009712470000522444, "children": { "_process_rank_one_or_two_observation": { "total": 0.003395875000023807, "count": 8, "is_parallel": true, "self": 0.003395875000023807 } } } } } } }, "UnityEnvironment.step": { "total": 3862.138409503892, "count": 217139, "is_parallel": true, "self": 241.28927529279463, "children": { "UnityEnvironment._generate_step_input": { "total": 155.75392822585468, "count": 217139, "is_parallel": true, "self": 155.75392822585468 }, "communicator.exchange": { "total": 2679.8319202666794, "count": 217139, "is_parallel": true, "self": 2679.8319202666794 }, "steps_from_proto": { "total": 785.2632857185636, "count": 434278, "is_parallel": true, "self": 127.32571072626911, "children": { "_process_rank_one_or_two_observation": { "total": 657.9375749922945, "count": 1737112, "is_parallel": true, "self": 657.9375749922945 } } } } }, "steps_from_proto": { "total": 0.042569369001057566, "count": 32, "is_parallel": true, "self": 0.007627899004774008, "children": { "_process_rank_one_or_two_observation": { "total": 0.03494146999628356, "count": 128, "is_parallel": true, "self": 0.03494146999628356 } } } } } } } } }, "trainer_advance": { "total": 1450.6490810322755, "count": 217140, "self": 45.94307689031166, "children": { "process_trajectory": { "total": 348.396557200962, "count": 217140, "self": 346.283749084962, "children": { "RLTrainer._checkpoint": { "total": 2.1128081159999965, "count": 6, "self": 2.1128081159999965 } } }, "_update_policy": { "total": 1056.3094469410019, "count": 155, "self": 691.33450063696, "children": { "TorchPOCAOptimizer.update": { "total": 364.97494630404185, "count": 4652, "self": 364.97494630404185 } } } } } } }, "trainer_threads": { "total": 1.525000698165968e-06, "count": 1, "self": 1.525000698165968e-06 }, "TrainerController._save_models": { "total": 0.6994637449988659, "count": 1, "self": 0.0023628199996892363, "children": { "RLTrainer._checkpoint": { "total": 0.6971009249991766, "count": 1, "self": 0.6971009249991766 } } } } } } }