{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8955084085464478, "min": 1.8422900438308716, "max": 2.093956708908081, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38456.07421875, "min": 33440.90625, "max": 47368.375, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.3013698630137, "min": 49.77906976744186, "max": 104.18367346938776, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19652.0, "min": 17124.0, "max": 22200.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1551.8239050312495, "min": 1488.0337250922112, "max": 1560.0137722228626, "count": 200 }, "SoccerTwos.Self-play.ELO.sum": { "value": 226566.29013456244, "min": 148296.2012005081, "max": 288932.1385805928, "count": 200 }, "SoccerTwos.Step.mean": { "value": 9999976.0, "min": 8009970.0, "max": 9999976.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 9999976.0, "min": 8009970.0, "max": 9999976.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07242073118686676, "min": -0.16348804533481598, "max": 0.13070540130138397, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.573427200317383, "min": -27.629480361938477, "max": 19.082988739013672, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07825343310832977, "min": -0.16575385630130768, "max": 0.131241574883461, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 11.42500114440918, "min": -28.012401580810547, "max": 19.161270141601562, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.16666301145945508, "min": -0.40307586234191367, "max": 0.28878254124096464, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 24.332799673080444, "min": -58.446000039577484, "max": 45.171999752521515, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.16666301145945508, "min": -0.40307586234191367, "max": 0.28878254124096464, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 24.332799673080444, "min": -58.446000039577484, "max": 45.171999752521515, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.025021878300079455, "min": 0.021023620530225648, "max": 0.03315305429860018, "count": 193 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.025021878300079455, "min": 0.021023620530225648, "max": 0.03315305429860018, "count": 193 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07110492245604595, "min": 0.05825461180259784, "max": 0.09087043926119805, "count": 193 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07110492245604595, "min": 0.05825461180259784, "max": 0.09087043926119805, "count": 193 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08191935482124488, "min": 0.06437495543311039, "max": 0.10171770788729191, "count": 193 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08191935482124488, "min": 0.06437495543311039, "max": 0.10171770788729191, "count": 193 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 193 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 193 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 193 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 193 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 193 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 193 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718883158", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718888181" }, "total": 5022.471962849, "count": 1, "self": 0.46395551200021146, "children": { "run_training.setup": { "total": 0.05602131899996721, "count": 1, "self": 0.05602131899996721 }, "TrainerController.start_learning": { "total": 5021.951986018, "count": 1, "self": 3.1320614599881083, "children": { "TrainerController._reset_env": { "total": 3.3683689129991876, "count": 11, "self": 3.3683689129991876 }, "TrainerController.advance": { "total": 5015.155259341012, "count": 137247, "self": 3.408958867018555, "children": { "env_step": { "total": 3409.571973765003, "count": 137247, "self": 2592.642890049901, "children": { "SubprocessEnvManager._take_step": { "total": 815.1041082270739, "count": 137247, "self": 20.74925583620177, "children": { "TorchPolicy.evaluate": { "total": 794.3548523908721, "count": 250996, "self": 794.3548523908721 } } }, "workers": { "total": 1.8249754880282012, "count": 137247, "self": 0.0, "children": { "worker_root": { "total": 5013.951839441042, "count": 137247, "is_parallel": true, "self": 2835.7990415421054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007442628000035256, "count": 2, "is_parallel": true, "self": 0.004348741000001155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030938870000341012, "count": 8, "is_parallel": true, "self": 0.0030938870000341012 } } }, "UnityEnvironment.step": { "total": 0.038657415999978184, "count": 1, "is_parallel": true, "self": 0.0011664620000146897, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008400569999480467, "count": 1, "is_parallel": true, "self": 0.0008400569999480467 }, "communicator.exchange": { "total": 0.03322824299999638, "count": 1, "is_parallel": true, "self": 0.03322824299999638 }, "steps_from_proto": { "total": 0.0034226540000190653, "count": 2, "is_parallel": true, "self": 0.0005984359999047228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028242180001143424, "count": 8, "is_parallel": true, "self": 0.0028242180001143424 } } } } } } }, "steps_from_proto": { "total": 0.02078374899940627, "count": 20, "is_parallel": true, "self": 0.00429572499774622, "children": { "_process_rank_one_or_two_observation": { "total": 0.01648802400166005, "count": 80, "is_parallel": true, "self": 0.01648802400166005 } } }, "UnityEnvironment.step": { "total": 2178.132014149937, "count": 137246, "is_parallel": true, "self": 137.4480117038629, "children": { "UnityEnvironment._generate_step_input": { "total": 91.87265370296143, "count": 137246, "is_parallel": true, "self": 91.87265370296143 }, "communicator.exchange": { "total": 1517.5340509910097, "count": 137246, "is_parallel": true, "self": 1517.5340509910097 }, "steps_from_proto": { "total": 431.27729775210275, "count": 274492, "is_parallel": true, "self": 71.7870211804086, "children": { "_process_rank_one_or_two_observation": { "total": 359.49027657169415, "count": 1097968, "is_parallel": true, "self": 359.49027657169415 } } } } } } } } } } }, "trainer_advance": { "total": 1602.1743267089912, "count": 137247, "self": 24.812080927036504, "children": { "process_trajectory": { "total": 455.18851799195363, "count": 137247, "self": 453.81507471995315, "children": { "RLTrainer._checkpoint": { "total": 1.373443272000486, "count": 4, "self": 1.373443272000486 } } }, "_update_policy": { "total": 1122.173727790001, "count": 193, "self": 609.1868159890051, "children": { "TorchPOCAOptimizer.update": { "total": 512.9869118009959, "count": 11580, "self": 512.9869118009959 } } } } } } }, "trainer_threads": { "total": 8.120005077216774e-07, "count": 1, "self": 8.120005077216774e-07 }, "TrainerController._save_models": { "total": 0.2962954919994445, "count": 1, "self": 0.005442683999717701, "children": { "RLTrainer._checkpoint": { "total": 0.2908528079997268, "count": 1, "self": 0.2908528079997268 } } } } } } }