{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.72711181640625, "min": 1.671557068824768, "max": 3.295755386352539, "count": 784 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35371.25, "min": 16988.4453125, "max": 109470.1875, "count": 784 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.25, "min": 41.05084745762712, "max": 999.0, "count": 784 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19836.0, "min": 11988.0, "max": 25940.0, "count": 784 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.1742045247136, "min": 1192.3536352246779, "max": 1607.6897156320813, "count": 750 }, "SoccerTwos.Self-play.ELO.sum": { "value": 243530.47908775645, "min": 2384.7072704493557, "max": 377309.4046767551, "count": 750 }, "SoccerTwos.Step.mean": { "value": 7839848.0, "min": 9990.0, "max": 7839848.0, "count": 784 }, "SoccerTwos.Step.sum": { "value": 7839848.0, "min": 9990.0, "max": 7839848.0, "count": 784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0023163086734712124, "min": -0.10220928490161896, "max": 0.16093367338180542, "count": 784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.352078914642334, "min": -20.237438201904297, "max": 23.81818389892578, "count": 784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0004817843437194824, "min": -0.09853282570838928, "max": 0.16025327146053314, "count": 784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.07323122024536133, "min": -18.909896850585938, "max": 23.717483520507812, "count": 784 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 784 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 784 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09625526399988878, "min": -0.7386344835675996, "max": 0.5267655150643711, "count": 784 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 14.630800127983093, "min": -65.3808000087738, "max": 58.02219998836517, "count": 784 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09625526399988878, "min": -0.7386344835675996, "max": 0.5267655150643711, "count": 784 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 14.630800127983093, "min": -65.3808000087738, "max": 58.02219998836517, "count": 784 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 784 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 784 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01764298015429328, "min": 0.010950238690323506, "max": 0.022482394275721164, "count": 377 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01764298015429328, "min": 0.010950238690323506, "max": 0.022482394275721164, "count": 377 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09807224869728089, "min": 4.585030543087972e-07, "max": 0.1255581816037496, "count": 377 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09807224869728089, "min": 4.585030543087972e-07, "max": 0.1255581816037496, "count": 377 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09944819311300913, "min": 4.424588117520519e-07, "max": 0.1275894212226073, "count": 377 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09944819311300913, "min": 4.424588117520519e-07, "max": 0.1275894212226073, "count": 377 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 377 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 377 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 377 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 377 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 377 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 377 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710442512", "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\\amber\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710454283" }, "total": 11770.568508300013, "count": 1, "self": 0.1466140000266023, "children": { "run_training.setup": { "total": 0.04752399999415502, "count": 1, "self": 0.04752399999415502 }, "TrainerController.start_learning": { "total": 11770.374370299993, "count": 1, "self": 7.355365001145401, "children": { "TrainerController._reset_env": { "total": 4.624762799954624, "count": 40, "self": 4.624762799954624 }, "TrainerController.advance": { "total": 11758.247405398884, "count": 534775, "self": 7.542019303058623, "children": { "env_step": { "total": 5282.786133503381, "count": 534775, "self": 4117.349457297823, "children": { "SubprocessEnvManager._take_step": { "total": 1160.7886641996301, "count": 534775, "self": 46.50264438748127, "children": { "TorchPolicy.evaluate": { "total": 1114.2860198121489, "count": 991630, "self": 1114.2860198121489 } } }, "workers": { "total": 4.64801200592774, "count": 534774, "self": 0.0, "children": { "worker_root": { "total": 11757.757449391793, "count": 534774, "is_parallel": true, "self": 8455.259314197727, "children": { "steps_from_proto": { "total": 0.040848600037861615, "count": 80, "is_parallel": true, "self": 0.008222899836255237, "children": { "_process_rank_one_or_two_observation": { "total": 0.03262570020160638, "count": 320, "is_parallel": true, "self": 0.03262570020160638 } } }, "UnityEnvironment.step": { "total": 3302.457286594028, "count": 534774, "is_parallel": true, "self": 156.80489337674226, "children": { "UnityEnvironment._generate_step_input": { "total": 115.85295320823207, "count": 534774, "is_parallel": true, "self": 115.85295320823207 }, "communicator.exchange": { "total": 2535.0331652071036, "count": 534774, "is_parallel": true, "self": 2535.0331652071036 }, "steps_from_proto": { "total": 494.7662748019502, "count": 1069548, "is_parallel": true, "self": 97.41217780351872, "children": { "_process_rank_one_or_two_observation": { "total": 397.3540969984315, "count": 4278192, "is_parallel": true, "self": 397.3540969984315 } } } } } } } } } } }, "trainer_advance": { "total": 6467.9192525924445, "count": 534774, "self": 57.76235199844814, "children": { "process_trajectory": { "total": 1269.3616613940394, "count": 534774, "self": 1268.0420684940618, "children": { "RLTrainer._checkpoint": { "total": 1.3195928999775788, "count": 15, "self": 1.3195928999775788 } } }, "_update_policy": { "total": 5140.795239199957, "count": 377, "self": 706.3808342998964, "children": { "TorchPOCAOptimizer.update": { "total": 4434.414404900061, "count": 11316, "self": 4434.414404900061 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.14683630000217818, "count": 1, "self": 0.0026784000074258074, "children": { "RLTrainer._checkpoint": { "total": 0.14415789999475237, "count": 1, "self": 0.14415789999475237 } } } } } } }