{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2696778774261475, "min": 3.2696778774261475, "max": 3.295753002166748, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 82343.5703125, "min": 44060.8828125, "max": 105464.09375, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 727.8333333333334, "min": 590.5, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17468.0, "min": 4724.0, "max": 31968.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.3192679027218, "min": 1198.3192679027218, "max": 1200.3689776363867, "count": 9 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9586.554143221774, "min": 2397.9801952086127, "max": 9591.965857908112, "count": 9 }, "SoccerTwos.Step.mean": { "value": 99381.0, "min": 9584.0, "max": 99381.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99381.0, "min": 9584.0, "max": 99381.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0437549352645874, "min": -0.07337113469839096, "max": -0.0437549352645874, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5688141584396362, "min": -0.9163175225257874, "max": -0.5090833902359009, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04437267407774925, "min": -0.07342542707920074, "max": -0.04437267407774925, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.5768447518348694, "min": -0.8945850133895874, "max": -0.5112509727478027, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.22533846245362207, "min": -0.2826857141086033, "max": 0.07639999958601865, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.929400011897087, "min": -3.9575999975204468, "max": 0.8403999954462051, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.22533846245362207, "min": -0.2826857141086033, "max": 0.07639999958601865, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.929400011897087, "min": -3.9575999975204468, "max": 0.8403999954462051, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015225912048481404, "min": 0.014602835137685318, "max": 0.016029355120069037, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015225912048481404, "min": 0.014602835137685318, "max": 0.016029355120069037, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0018669080648881693, "min": 0.0016783606517405826, "max": 0.004392762575298548, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0018669080648881693, "min": 0.0016783606517405826, "max": 0.004392762575298548, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0019107467533710102, "min": 0.0014240537226820986, "max": 0.004455769644118845, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0019107467533710102, "min": 0.0014240537226820986, "max": 0.004455769644118845, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730912221", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\K.Mikhailov\\AppData\\Local\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1730912549" }, "total": 327.82158280000294, "count": 1, "self": 0.9260648000054061, "children": { "run_training.setup": { "total": 0.11618769999768119, "count": 1, "self": 0.11618769999768119 }, "TrainerController.start_learning": { "total": 326.77933029999986, "count": 1, "self": 0.20002060011029243, "children": { "TrainerController._reset_env": { "total": 5.063689199996588, "count": 1, "self": 5.063689199996588 }, "TrainerController.advance": { "total": 321.272164999893, "count": 6824, "self": 0.1894599995939643, "children": { "env_step": { "total": 157.59721720013476, "count": 6824, "self": 123.87716779967741, "children": { "SubprocessEnvManager._take_step": { "total": 33.5906568003993, "count": 6824, "self": 1.0147750005999114, "children": { "TorchPolicy.evaluate": { "total": 32.57588179979939, "count": 13574, "self": 32.57588179979939 } } }, "workers": { "total": 0.12939260005805409, "count": 6824, "self": 0.0, "children": { "worker_root": { "total": 322.2273354001809, "count": 6824, "is_parallel": true, "self": 224.17855320023955, "children": { "steps_from_proto": { "total": 0.001918899994052481, "count": 2, "is_parallel": true, "self": 0.00037459998566191643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015443000083905645, "count": 8, "is_parallel": true, "self": 0.0015443000083905645 } } }, "UnityEnvironment.step": { "total": 98.04686329994729, "count": 6824, "is_parallel": true, "self": 5.167755800204759, "children": { "UnityEnvironment._generate_step_input": { "total": 4.0627230002428405, "count": 6824, "is_parallel": true, "self": 4.0627230002428405 }, "communicator.exchange": { "total": 71.62522349983192, "count": 6824, "is_parallel": true, "self": 71.62522349983192 }, "steps_from_proto": { "total": 17.191160999667773, "count": 13648, "is_parallel": true, "self": 3.3366357003178564, "children": { "_process_rank_one_or_two_observation": { "total": 13.854525299349916, "count": 54592, "is_parallel": true, "self": 13.854525299349916 } } } } } } } } } } }, "trainer_advance": { "total": 163.48548780016426, "count": 6824, "self": 1.197419000280206, "children": { "process_trajectory": { "total": 23.392365599887853, "count": 6824, "self": 23.392365599887853 }, "_update_policy": { "total": 138.8957031999962, "count": 4, "self": 15.92536030003248, "children": { "TorchPOCAOptimizer.update": { "total": 122.97034289996373, "count": 132, "self": 122.97034289996373 } } } } } } }, "trainer_threads": { "total": 1.500004145782441e-06, "count": 1, "self": 1.500004145782441e-06 }, "TrainerController._save_models": { "total": 0.24345399999583606, "count": 1, "self": 0.013574499993410427, "children": { "RLTrainer._checkpoint": { "total": 0.22987950000242563, "count": 1, "self": 0.22987950000242563 } } } } } } }