{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2021987438201904, "min": 3.1849381923675537, "max": 3.295734405517578, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54001.87890625, "min": 26173.83203125, "max": 128278.6015625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 661.875, "min": 424.7, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21180.0, "min": 13472.0, "max": 27904.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1206.0864710019525, "min": 1194.9835714627477, "max": 1206.3730028454006, "count": 47 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7236.518826011715, "min": 2392.00433112584, "max": 19189.630617188253, "count": 47 }, "SoccerTwos.Step.mean": { "value": 499880.0, "min": 9970.0, "max": 499880.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499880.0, "min": 9970.0, "max": 499880.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004247588105499744, "min": -0.03798258677124977, "max": -0.004247588105499744, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.06796140968799591, "min": -0.5678527355194092, "max": -0.06796140968799591, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0032599333208054304, "min": -0.03796309232711792, "max": -0.0032599333208054304, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.05215893313288689, "min": -0.5768260359764099, "max": -0.04636053740978241, "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": -0.1285500004887581, "min": -0.4117647058823529, "max": 0.423788243356873, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0568000078201294, "min": -7.0, "max": 7.204400137066841, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1285500004887581, "min": -0.4117647058823529, "max": 0.423788243356873, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0568000078201294, "min": -7.0, "max": 7.204400137066841, "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": 0.013603253200805436, "min": 0.012844269606284797, "max": 0.021047743995829173, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013603253200805436, "min": 0.012844269606284797, "max": 0.021047743995829173, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002780951140448451, "min": 0.00047950857054577986, "max": 0.005121187547532221, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002780951140448451, "min": 0.00047950857054577986, "max": 0.005121187547532221, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0027876447536982598, "min": 0.00047923519741743803, "max": 0.005321657129873832, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0027876447536982598, "min": 0.00047923519741743803, "max": 0.005321657129873832, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0002970283569905479, "min": 0.0002970283569905479, "max": 0.00029987571604142793, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0002970283569905479, "min": 0.0002970283569905479, "max": 0.00029987571604142793, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19900945200000006, "min": 0.19900945200000006, "max": 0.19995857199999997, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19900945200000006, "min": 0.19900945200000006, "max": 0.19995857199999997, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0049505716548000015, "min": 0.0049505716548000015, "max": 0.0049979327428, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0049505716548000015, "min": 0.0049505716548000015, "max": 0.0049979327428, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681404854", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\deeprl\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1681406693" }, "total": 1838.6563569999998, "count": 1, "self": 2.704541099999915, "children": { "run_training.setup": { "total": 0.09266970000000008, "count": 1, "self": 0.09266970000000008 }, "TrainerController.start_learning": { "total": 1835.8591462, "count": 1, "self": 0.7374962999974741, "children": { "TrainerController._reset_env": { "total": 20.705541299999943, "count": 3, "self": 20.705541299999943 }, "TrainerController.advance": { "total": 1814.2852073000024, "count": 33005, "self": 0.7289156999938768, "children": { "env_step": { "total": 568.914050300004, "count": 33005, "self": 441.9557542999979, "children": { "SubprocessEnvManager._take_step": { "total": 126.45227609999402, "count": 33005, "self": 4.533149599983361, "children": { "TorchPolicy.evaluate": { "total": 121.91912650001066, "count": 65490, "self": 121.91912650001066 } } }, "workers": { "total": 0.5060199000120562, "count": 33005, "self": 0.0, "children": { "worker_root": { "total": 1813.6383169999983, "count": 33005, "is_parallel": true, "self": 1463.3373093999942, "children": { "steps_from_proto": { "total": 0.012366400000029643, "count": 6, "is_parallel": true, "self": 0.0030219999995821922, "children": { "_process_rank_one_or_two_observation": { "total": 0.00934440000044745, "count": 24, "is_parallel": true, "self": 0.00934440000044745 } } }, "UnityEnvironment.step": { "total": 350.2886412000041, "count": 33005, "is_parallel": true, "self": 18.607390999974825, "children": { "UnityEnvironment._generate_step_input": { "total": 15.851795000005815, "count": 33005, "is_parallel": true, "self": 15.851795000005815 }, "communicator.exchange": { "total": 255.00962690001762, "count": 33005, "is_parallel": true, "self": 255.00962690001762 }, "steps_from_proto": { "total": 60.81982830000584, "count": 66010, "is_parallel": true, "self": 10.716681199992735, "children": { "_process_rank_one_or_two_observation": { "total": 50.1031471000131, "count": 264040, "is_parallel": true, "self": 50.1031471000131 } } } } } } } } } } }, "trainer_advance": { "total": 1244.6422413000046, "count": 33005, "self": 6.15210929999057, "children": { "process_trajectory": { "total": 153.97772000001294, "count": 33005, "self": 153.38620850001314, "children": { "RLTrainer._checkpoint": { "total": 0.5915114999997968, "count": 1, "self": 0.5915114999997968 } } }, "_update_policy": { "total": 1084.5124120000012, "count": 23, "self": 82.61968610000042, "children": { "TorchPOCAOptimizer.update": { "total": 1001.8927259000008, "count": 690, "self": 1001.8927259000008 } } } } } } }, "TrainerController._save_models": { "total": 0.130901300000005, "count": 1, "self": 3.59000000571541e-05, "children": { "RLTrainer._checkpoint": { "total": 0.13086539999994784, "count": 1, "self": 0.13086539999994784 } } } } } } }