{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.409071922302246, "min": 0.580023467540741, "max": 3.2957353591918945, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28406.890625, "min": 5988.8271484375, "max": 145126.765625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.3972602739726, "min": 44.054545454545455, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20264.0, "min": 12164.0, "max": 27920.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1542.8781649418193, "min": 1184.7955637147627, "max": 1625.1740943820848, "count": 3265 }, "SoccerTwos.Self-play.ELO.sum": { "value": 225260.21208150563, "min": 2374.3217125616216, "max": 351378.12929364503, "count": 3265 }, "SoccerTwos.Step.mean": { "value": 49999902.0, "min": 9976.0, "max": 49999902.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999902.0, "min": 9976.0, "max": 49999902.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04849886894226074, "min": -0.14891868829727173, "max": 0.197387233376503, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.032336235046387, "min": -25.018339157104492, "max": 21.909982681274414, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04817768931388855, "min": -0.14785706996917725, "max": 0.19496957957744598, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.985764980316162, "min": -24.83998680114746, "max": 21.64162254333496, "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": -0.14953103558770542, "min": -0.5992666681607565, "max": 0.4935333345617567, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.682000160217285, "min": -59.1327999830246, "max": 46.43540012836456, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14953103558770542, "min": -0.5992666681607565, "max": 0.4935333345617567, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.682000160217285, "min": -59.1327999830246, "max": 46.43540012836456, "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": 0.018001814029412345, "min": 0.009255766456529575, "max": 0.026368796251093347, "count": 2370 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018001814029412345, "min": 0.009255766456529575, "max": 0.026368796251093347, "count": 2370 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08666058033704757, "min": 3.279833690518948e-11, "max": 0.11784214849273364, "count": 2370 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08666058033704757, "min": 3.279833690518948e-11, "max": 0.11784214849273364, "count": 2370 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08756576379140218, "min": 3.7002813429073043e-11, "max": 0.11892481545607249, "count": 2370 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08756576379140218, "min": 3.7002813429073043e-11, "max": 0.11892481545607249, "count": 2370 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2370 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2370 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2370 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2370 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2370 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2370 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705906520", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706014077" }, "total": 107556.39236933202, "count": 1, "self": 0.4893856640555896, "children": { "run_training.setup": { "total": 0.09685415698913857, "count": 1, "self": 0.09685415698913857 }, "TrainerController.start_learning": { "total": 107555.80612951098, "count": 1, "self": 56.057607389520854, "children": { "TrainerController._reset_env": { "total": 12.113171444681939, "count": 250, "self": 12.113171444681939 }, "TrainerController.advance": { "total": 107487.14703818178, "count": 3358224, "self": 53.167223570810165, "children": { "env_step": { "total": 47161.045734404994, "count": 3358224, "self": 37205.82435472682, "children": { "SubprocessEnvManager._take_step": { "total": 9922.062924618716, "count": 3358224, "self": 372.13904499076307, "children": { "TorchPolicy.evaluate": { "total": 9549.923879627953, "count": 6350498, "self": 9549.923879627953 } } }, "workers": { "total": 33.15845505945617, "count": 3358224, "self": 0.0, "children": { "worker_root": { "total": 107466.25550758577, "count": 3358224, "is_parallel": true, "self": 77240.05800597148, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024395579821430147, "count": 2, "is_parallel": true, "self": 0.0007359739975072443, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017035839846357703, "count": 8, "is_parallel": true, "self": 0.0017035839846357703 } } }, "UnityEnvironment.step": { "total": 0.02229533198988065, "count": 1, "is_parallel": true, "self": 0.0005469299503602087, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004575889906845987, "count": 1, "is_parallel": true, "self": 0.0004575889906845987 }, "communicator.exchange": { "total": 0.019752520020119846, "count": 1, "is_parallel": true, "self": 0.019752520020119846 }, "steps_from_proto": { "total": 0.001538293028715998, "count": 2, "is_parallel": true, "self": 0.0003324220306240022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012058709980919957, "count": 8, "is_parallel": true, "self": 0.0012058709980919957 } } } } } } }, "UnityEnvironment.step": { "total": 30225.796755509567, "count": 3358223, "is_parallel": true, "self": 1597.375346368237, "children": { "UnityEnvironment._generate_step_input": { "total": 1068.764909645426, "count": 3358223, "is_parallel": true, "self": 1068.764909645426 }, "communicator.exchange": { "total": 22985.073879790318, "count": 3358223, "is_parallel": true, "self": 22985.073879790318 }, "steps_from_proto": { "total": 4574.582619705587, "count": 6716446, "is_parallel": true, "self": 858.5062123311218, "children": { "_process_rank_one_or_two_observation": { "total": 3716.076407374465, "count": 26865784, "is_parallel": true, "self": 3716.076407374465 } } } } }, "steps_from_proto": { "total": 0.40074610471492633, "count": 498, "is_parallel": true, "self": 0.07684651366434991, "children": { "_process_rank_one_or_two_observation": { "total": 0.3238995910505764, "count": 1992, "is_parallel": true, "self": 0.3238995910505764 } } } } } } } } }, "trainer_advance": { "total": 60272.934080205974, "count": 3358224, "self": 490.5562912662863, "children": { "process_trajectory": { "total": 9244.681141626206, "count": 3358224, "self": 9102.18898997939, "children": { "RLTrainer._checkpoint": { "total": 142.49215164681664, "count": 100, "self": 142.49215164681664 } } }, "_update_policy": { "total": 50537.69664731348, "count": 2370, "self": 5545.043199257401, "children": { "TorchPOCAOptimizer.update": { "total": 44992.65344805608, "count": 71109, "self": 44992.65344805608 } } } } } } }, "trainer_threads": { "total": 8.729984983801842e-07, "count": 1, "self": 8.729984983801842e-07 }, "TrainerController._save_models": { "total": 0.48831162200076506, "count": 1, "self": 0.010910457989666611, "children": { "RLTrainer._checkpoint": { "total": 0.47740116401109844, "count": 1, "self": 0.47740116401109844 } } } } } } }