{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.347036600112915, "min": 1.2690355777740479, "max": 3.295771598815918, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27889.046875, "min": 15704.1669921875, "max": 154574.09375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.576470588235296, "min": 40.48360655737705, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19916.0, "min": 16232.0, "max": 25176.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1682.3302431070465, "min": 1180.0864163496158, "max": 1769.0053013926174, "count": 4805 }, "SoccerTwos.Self-play.ELO.sum": { "value": 285996.1413281979, "min": 2361.1670866252966, "max": 402097.11283217557, "count": 4805 }, "SoccerTwos.Step.mean": { "value": 49999904.0, "min": 9606.0, "max": 49999904.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999904.0, "min": 9606.0, "max": 49999904.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03184669837355614, "min": -0.14862856268882751, "max": 0.17995670437812805, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.382091999053955, "min": -24.523712158203125, "max": 24.188234329223633, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.032041966915130615, "min": -0.15108972787857056, "max": 0.18417219817638397, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.415092468261719, "min": -24.94078826904297, "max": 25.135684967041016, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09725562178876979, "min": -0.5714285714285714, "max": 0.5946863632310521, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.436200082302094, "min": -69.38199985027313, "max": 67.41999995708466, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09725562178876979, "min": -0.5714285714285714, "max": 0.5946863632310521, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.436200082302094, "min": -69.38199985027313, "max": 67.41999995708466, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016061531269224362, "min": 0.009867382691785073, "max": 0.025753002444980667, "count": 2417 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016061531269224362, "min": 0.009867382691785073, "max": 0.025753002444980667, "count": 2417 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0999513973792394, "min": 4.8254725015794973e-08, "max": 0.12561291108528774, "count": 2417 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0999513973792394, "min": 4.8254725015794973e-08, "max": 0.12561291108528774, "count": 2417 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10045713807145755, "min": 5.4563187982618425e-08, "max": 0.12718206718564035, "count": 2417 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10045713807145755, "min": 5.4563187982618425e-08, "max": 0.12718206718564035, "count": 2417 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2417 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2417 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2417 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2417 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2417 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2417 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687354224", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/kejia/01_work/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1687431977" }, "total": 77752.132843518, "count": 1, "self": 0.2706062859942904, "children": { "run_training.setup": { "total": 0.012899744000151259, "count": 1, "self": 0.012899744000151259 }, "TrainerController.start_learning": { "total": 77751.849337488, "count": 1, "self": 63.739841922099004, "children": { "TrainerController._reset_env": { "total": 8.851859242075534, "count": 250, "self": 8.851859242075534 }, "TrainerController.advance": { "total": 77678.95592143483, "count": 3433199, "self": 65.65787351402105, "children": { "env_step": { "total": 57810.50003577653, "count": 3433199, "self": 42167.6887678804, "children": { "SubprocessEnvManager._take_step": { "total": 15604.982782657968, "count": 3433199, "self": 429.27984591477434, "children": { "TorchPolicy.evaluate": { "total": 15175.702936743193, "count": 6292228, "self": 15175.702936743193 } } }, "workers": { "total": 37.828485238168014, "count": 3433199, "self": 0.0, "children": { "worker_root": { "total": 77611.41751427937, "count": 3433199, "is_parallel": true, "self": 43000.622320891256, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031274900002244976, "count": 2, "is_parallel": true, "self": 0.0007344740006374195, "children": { "_process_rank_one_or_two_observation": { "total": 0.002393015999587078, "count": 8, "is_parallel": true, "self": 0.002393015999587078 } } }, "UnityEnvironment.step": { "total": 0.027826115999687318, "count": 1, "is_parallel": true, "self": 0.0006064789999982168, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004882819998783816, "count": 1, "is_parallel": true, "self": 0.0004882819998783816 }, "communicator.exchange": { "total": 0.0235298679999687, "count": 1, "is_parallel": true, "self": 0.0235298679999687 }, "steps_from_proto": { "total": 0.003201486999842018, "count": 2, "is_parallel": true, "self": 0.0011092610002378933, "children": { "_process_rank_one_or_two_observation": { "total": 0.002092225999604125, "count": 8, "is_parallel": true, "self": 0.002092225999604125 } } } } } } }, "UnityEnvironment.step": { "total": 34610.34975866321, "count": 3433198, "is_parallel": true, "self": 1804.5499278566276, "children": { "UnityEnvironment._generate_step_input": { "total": 1190.446759735783, "count": 3433198, "is_parallel": true, "self": 1190.446759735783 }, "communicator.exchange": { "total": 26051.2008201062, "count": 3433198, "is_parallel": true, "self": 26051.2008201062 }, "steps_from_proto": { "total": 5564.1522509645965, "count": 6866396, "is_parallel": true, "self": 1192.1637758689494, "children": { "_process_rank_one_or_two_observation": { "total": 4371.988475095647, "count": 27465584, "is_parallel": true, "self": 4371.988475095647 } } } } }, "steps_from_proto": { "total": 0.44543472490204294, "count": 498, "is_parallel": true, "self": 0.09592068305028079, "children": { "_process_rank_one_or_two_observation": { "total": 0.34951404185176216, "count": 1992, "is_parallel": true, "self": 0.34951404185176216 } } } } } } } } }, "trainer_advance": { "total": 19802.798012144267, "count": 3433199, "self": 440.0194110431803, "children": { "process_trajectory": { "total": 8660.09415681116, "count": 3433199, "self": 8632.725306058106, "children": { "RLTrainer._checkpoint": { "total": 27.36885075305372, "count": 100, "self": 27.36885075305372 } } }, "_update_policy": { "total": 10702.684444289927, "count": 2417, "self": 7641.828680424076, "children": { "TorchPOCAOptimizer.update": { "total": 3060.855763865851, "count": 72510, "self": 3060.855763865851 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.3017138889990747, "count": 1, "self": 0.0015715390036348253, "children": { "RLTrainer._checkpoint": { "total": 0.30014234999543987, "count": 1, "self": 0.30014234999543987 } } } } } } }