{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9291170835494995, "min": 1.8552395105361938, "max": 3.2957236766815186, "count": 1180 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39261.390625, "min": 18268.6484375, "max": 146873.828125, "count": 1180 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.11363636363637, "min": 40.12, "max": 999.0, "count": 1180 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20104.0, "min": 10500.0, "max": 29024.0, "count": 1180 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1658.209464932352, "min": 1189.585084023995, "max": 1725.188051107122, "count": 1156 }, "SoccerTwos.Self-play.ELO.sum": { "value": 291844.86582809396, "min": 2381.9127099984767, "max": 407354.7901875677, "count": 1156 }, "SoccerTwos.Step.mean": { "value": 11799924.0, "min": 9448.0, "max": 11799924.0, "count": 1180 }, "SoccerTwos.Step.sum": { "value": 11799924.0, "min": 9448.0, "max": 11799924.0, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.049491703510284424, "min": -0.10328812152147293, "max": 0.18030281364917755, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.66104793548584, "min": -14.271673202514648, "max": 24.303085327148438, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05083049088716507, "min": -0.10325547307729721, "max": 0.18770861625671387, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.895336151123047, "min": -14.213946342468262, "max": 25.439725875854492, "count": 1180 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1180 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14695199932370867, "min": -0.6272461528961475, "max": 0.7841285753006838, "count": 1180 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.716599881649017, "min": -47.014200150966644, "max": 76.84460037946701, "count": 1180 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14695199932370867, "min": -0.6272461528961475, "max": 0.7841285753006838, "count": 1180 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.716599881649017, "min": -47.014200150966644, "max": 76.84460037946701, "count": 1180 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1180 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1180 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01856582779728342, "min": 0.008319745107049433, "max": 0.020095219637732954, "count": 285 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01856582779728342, "min": 0.008319745107049433, "max": 0.020095219637732954, "count": 285 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06312520131468773, "min": 0.0005722402932102947, "max": 0.07544807940721512, "count": 285 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06312520131468773, "min": 0.0005722402932102947, "max": 0.07544807940721512, "count": 285 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06485664981106917, "min": 0.0005708885793865193, "max": 0.07775571793317795, "count": 285 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06485664981106917, "min": 0.0005708885793865193, "max": 0.07775571793317795, "count": 285 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 285 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 285 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 285 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 285 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 285 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 285 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686108196", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\eaden\\miniconda3\\envs\\rlHuggingFace\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1686144921" }, "total": 36725.6045326, "count": 1, "self": 0.005228700007137377, "children": { "run_training.setup": { "total": 0.09423650000000006, "count": 1, "self": 0.09423650000000006 }, "TrainerController.start_learning": { "total": 36725.505067399994, "count": 1, "self": 15.754929300521326, "children": { "TrainerController._reset_env": { "total": 4.390641099989624, "count": 59, "self": 4.390641099989624 }, "TrainerController.advance": { "total": 36705.24884719948, "count": 805834, "self": 15.07107550198998, "children": { "env_step": { "total": 10308.16381749805, "count": 805834, "self": 8016.082624194722, "children": { "SubprocessEnvManager._take_step": { "total": 2282.847217702719, "count": 805834, "self": 80.76060490266991, "children": { "TorchPolicy.evaluate": { "total": 2202.086612800049, "count": 1487072, "self": 2202.086612800049 } } }, "workers": { "total": 9.23397560061084, "count": 805834, "self": 0.0, "children": { "worker_root": { "total": 36661.820653898125, "count": 805834, "is_parallel": true, "self": 30250.67168949754, "children": { "steps_from_proto": { "total": 0.08054820000879204, "count": 118, "is_parallel": true, "self": 0.01661829996981501, "children": { "_process_rank_one_or_two_observation": { "total": 0.06392990003897703, "count": 472, "is_parallel": true, "self": 0.06392990003897703 } } }, "UnityEnvironment.step": { "total": 6411.068416200578, "count": 805834, "is_parallel": true, "self": 325.3614903000116, "children": { "UnityEnvironment._generate_step_input": { "total": 232.41281130160502, "count": 805834, "is_parallel": true, "self": 232.41281130160502 }, "communicator.exchange": { "total": 4817.202108301453, "count": 805834, "is_parallel": true, "self": 4817.202108301453 }, "steps_from_proto": { "total": 1036.0920062975083, "count": 1611668, "is_parallel": true, "self": 215.1892200998243, "children": { "_process_rank_one_or_two_observation": { "total": 820.902786197684, "count": 6446672, "is_parallel": true, "self": 820.902786197684 } } } } } } } } } } }, "trainer_advance": { "total": 26382.013954199436, "count": 805834, "self": 112.60498300103427, "children": { "process_trajectory": { "total": 2283.8579623984297, "count": 805834, "self": 2281.2781560984286, "children": { "RLTrainer._checkpoint": { "total": 2.5798063000011098, "count": 23, "self": 2.5798063000011098 } } }, "_update_policy": { "total": 23985.551008799972, "count": 286, "self": 1531.1537574001086, "children": { "TorchPOCAOptimizer.update": { "total": 22454.397251399863, "count": 8565, "self": 22454.397251399863 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.1106489000012516, "count": 1, "self": 0.00529159999859985, "children": { "RLTrainer._checkpoint": { "total": 0.10535730000265175, "count": 1, "self": 0.10535730000265175 } } } } } } }