{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0632262229919434, "min": 2.9282093048095703, "max": 3.29571270942688, "count": 160 }, "SoccerTwos.Policy.Entropy.sum": { "value": 56363.36328125, "min": 1888.525634765625, "max": 116642.484375, "count": 160 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 547.25, "max": 999.0, "count": 160 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 3996.0, "max": 29432.0, "count": 160 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1208.5142513291294, "min": 1199.797190841213, "max": 1213.2577477031239, "count": 67 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2417.0285026582587, "min": 2405.6387479969494, "max": 14426.816311482966, "count": 67 }, "SoccerTwos.Step.mean": { "value": 1599850.0, "min": 9734.0, "max": 1599850.0, "count": 160 }, "SoccerTwos.Step.sum": { "value": 1599850.0, "min": 9734.0, "max": 1599850.0, "count": 160 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -7.28306476958096e-05, "min": -0.060920599848032, "max": 0.025008145719766617, "count": 160 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.000728306476958096, "min": -0.8535535335540771, "max": 0.25008144974708557, "count": 160 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -3.08988819597289e-05, "min": -0.0608757808804512, "max": 0.0230441614985466, "count": 160 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.00030898881959728897, "min": -0.8752724528312683, "max": 0.230441614985466, "count": 160 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 160 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 160 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.3712615382212859, "max": 0.2877294166999705, "count": 160 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -4.826399996876717, "max": 4.891400083899498, "count": 160 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.3712615382212859, "max": 0.2877294166999705, "count": 160 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -4.826399996876717, "max": 4.891400083899498, "count": 160 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 160 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 160 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016624411146040075, "min": 0.012897354683082085, "max": 0.02154538045094038, "count": 73 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016624411146040075, "min": 0.012897354683082085, "max": 0.02154538045094038, "count": 73 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.47029754518735e-07, "min": 8.167408106866484e-08, "max": 0.0053624828190853195, "count": 73 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.47029754518735e-07, "min": 8.167408106866484e-08, "max": 0.0053624828190853195, "count": 73 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.366686568204083e-07, "min": 8.656304425850673e-08, "max": 0.005449138449815412, "count": 73 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.366686568204083e-07, "min": 8.656304425850673e-08, "max": 0.005449138449815412, "count": 73 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 73 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 73 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 73 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 73 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 73 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 73 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680520047", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/panzhi/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-0403-2", "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": "1680520984" }, "total": 937.1262099719897, "count": 1, "self": 0.07988104499236215, "children": { "run_training.setup": { "total": 0.004342120999353938, "count": 1, "self": 0.004342120999353938 }, "TrainerController.start_learning": { "total": 937.041986805998, "count": 1, "self": 0.853711980409571, "children": { "TrainerController._reset_env": { "total": 3.8877620070124976, "count": 8, "self": 3.8877620070124976 }, "TrainerController.advance": { "total": 932.2143585855665, "count": 103756, "self": 0.8661760647082701, "children": { "env_step": { "total": 681.9046696157457, "count": 103756, "self": 534.6434713269555, "children": { "SubprocessEnvManager._take_step": { "total": 146.70816248185292, "count": 103756, "self": 5.8020147884235485, "children": { "TorchPolicy.evaluate": { "total": 140.90614769342938, "count": 206108, "self": 140.90614769342938 } } }, "workers": { "total": 0.5530358069372596, "count": 103755, "self": 0.0, "children": { "worker_root": { "total": 935.917623221394, "count": 103755, "is_parallel": true, "self": 501.2988266135508, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010792440007207915, "count": 2, "is_parallel": true, "self": 0.0002431750181131065, "children": { "_process_rank_one_or_two_observation": { "total": 0.000836068982607685, "count": 8, "is_parallel": true, "self": 0.000836068982607685 } } }, "UnityEnvironment.step": { "total": 0.011030762005248107, "count": 1, "is_parallel": true, "self": 0.0002671460242709145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019335999968461692, "count": 1, "is_parallel": true, "self": 0.00019335999968461692 }, "communicator.exchange": { "total": 0.009829322996665724, "count": 1, "is_parallel": true, "self": 0.009829322996665724 }, "steps_from_proto": { "total": 0.000740932984626852, "count": 2, "is_parallel": true, "self": 0.0001444009831175208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005965320015093312, "count": 8, "is_parallel": true, "self": 0.0005965320015093312 } } } } } } }, "UnityEnvironment.step": { "total": 434.61338344686374, "count": 103754, "is_parallel": true, "self": 27.273910639763926, "children": { "UnityEnvironment._generate_step_input": { "total": 15.488790573115693, "count": 103754, "is_parallel": true, "self": 15.488790573115693 }, "communicator.exchange": { "total": 320.30754160365905, "count": 103754, "is_parallel": true, "self": 320.30754160365905 }, "steps_from_proto": { "total": 71.54314063032507, "count": 207508, "is_parallel": true, "self": 12.578125334548531, "children": { "_process_rank_one_or_two_observation": { "total": 58.96501529577654, "count": 830032, "is_parallel": true, "self": 58.96501529577654 } } } } }, "steps_from_proto": { "total": 0.005413160979514942, "count": 14, "is_parallel": true, "self": 0.000992328001302667, "children": { "_process_rank_one_or_two_observation": { "total": 0.004420832978212275, "count": 56, "is_parallel": true, "self": 0.004420832978212275 } } } } } } } } }, "trainer_advance": { "total": 249.44351290511258, "count": 103755, "self": 7.553908242407488, "children": { "process_trajectory": { "total": 58.13956445074291, "count": 103755, "self": 57.88569903073949, "children": { "RLTrainer._checkpoint": { "total": 0.2538654200034216, "count": 3, "self": 0.2538654200034216 } } }, "_update_policy": { "total": 183.7500402119622, "count": 73, "self": 97.52730501358747, "children": { "TorchPOCAOptimizer.update": { "total": 86.22273519837472, "count": 2202, "self": 86.22273519837472 } } } } } } }, "trainer_threads": { "total": 4.5599881559610367e-07, "count": 1, "self": 4.5599881559610367e-07 }, "TrainerController._save_models": { "total": 0.08615377701062243, "count": 1, "self": 0.0006545890064444393, "children": { "RLTrainer._checkpoint": { "total": 0.085499188004178, "count": 1, "self": 0.085499188004178 } } } } } } }