{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5112178325653076, "min": 1.4550443887710571, "max": 3.2957026958465576, "count": 929 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28193.279296875, "min": 6817.09765625, "max": 115370.15625, "count": 929 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.85915492957747, "min": 37.64341085271318, "max": 999.0, "count": 929 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19556.0, "min": 3996.0, "max": 30336.0, "count": 929 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1604.2751922925138, "min": 1191.3060540824733, "max": 1639.8098799595462, "count": 921 }, "SoccerTwos.Self-play.ELO.sum": { "value": 227807.07730553695, "min": 2383.8214602694097, "max": 417643.9510141752, "count": 921 }, "SoccerTwos.Step.mean": { "value": 9289971.0, "min": 9236.0, "max": 9289971.0, "count": 929 }, "SoccerTwos.Step.sum": { "value": 9289971.0, "min": 9236.0, "max": 9289971.0, "count": 929 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012447405606508255, "min": -0.12627191841602325, "max": 0.20163512229919434, "count": 929 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.7799789905548096, "min": -26.01201629638672, "max": 37.30249786376953, "count": 929 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013726651668548584, "min": -0.13103096187114716, "max": 0.19688361883163452, "count": 929 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.9629111289978027, "min": -26.99237823486328, "max": 36.42346954345703, "count": 929 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 929 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 929 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.028352448990294984, "min": -0.631578947368421, "max": 0.44630256371620375, "count": 929 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.054400205612183, "min": -73.70879977941513, "max": 65.5147989988327, "count": 929 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.028352448990294984, "min": -0.631578947368421, "max": 0.44630256371620375, "count": 929 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.054400205612183, "min": -73.70879977941513, "max": 65.5147989988327, "count": 929 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 929 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 929 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014112015633145347, "min": 0.01134627233647431, "max": 0.024001921977226934, "count": 448 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014112015633145347, "min": 0.01134627233647431, "max": 0.024001921977226934, "count": 448 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10346591497461001, "min": 0.0002900623774621636, "max": 0.1367385797202587, "count": 448 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10346591497461001, "min": 0.0002900623774621636, "max": 0.1367385797202587, "count": 448 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10490976000825564, "min": 0.0002921819883340504, "max": 0.1405584176381429, "count": 448 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10490976000825564, "min": 0.0002921819883340504, "max": 0.1405584176381429, "count": 448 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 448 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 448 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 448 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 448 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 448 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 448 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726908023", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/applewang/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "2.4.1", "numpy_version": "1.23.5", "end_time_seconds": "1726934588" }, "total": 26565.178129000007, "count": 1, "self": 0.09012758400058374, "children": { "run_training.setup": { "total": 0.4649967079749331, "count": 1, "self": 0.4649967079749331 }, "TrainerController.start_learning": { "total": 26564.62300470803, "count": 1, "self": 5.512216902105138, "children": { "TrainerController._reset_env": { "total": 4.287491457012948, "count": 47, "self": 4.287491457012948 }, "TrainerController.advance": { "total": 26554.74454468087, "count": 646127, "self": 4.995779757737182, "children": { "env_step": { "total": 21410.067916036467, "count": 646127, "self": 20712.225156166125, "children": { "SubprocessEnvManager._take_step": { "total": 694.1660744313267, "count": 646127, "self": 22.008323678863235, "children": { "TorchPolicy.evaluate": { "total": 672.1577507524635, "count": 1168202, "self": 672.1577507524635 } } }, "workers": { "total": 3.676685439015273, "count": 646127, "self": 0.0, "children": { "worker_root": { "total": 26548.379569957906, "count": 646127, "is_parallel": true, "self": 6584.593463205092, "children": { "steps_from_proto": { "total": 0.05394041957333684, "count": 94, "is_parallel": true, "self": 0.0066166718024760485, "children": { "_process_rank_one_or_two_observation": { "total": 0.04732374777086079, "count": 376, "is_parallel": true, "self": 0.04732374777086079 } } }, "UnityEnvironment.step": { "total": 19963.73216633324, "count": 646127, "is_parallel": true, "self": 55.028023537714034, "children": { "UnityEnvironment._generate_step_input": { "total": 372.25428532867227, "count": 646127, "is_parallel": true, "self": 372.25428532867227 }, "communicator.exchange": { "total": 18852.889559973322, "count": 646127, "is_parallel": true, "self": 18852.889559973322 }, "steps_from_proto": { "total": 683.5602974935318, "count": 1292254, "is_parallel": true, "self": 80.48080466187093, "children": { "_process_rank_one_or_two_observation": { "total": 603.0794928316609, "count": 5169016, "is_parallel": true, "self": 603.0794928316609 } } } } } } } } } } }, "trainer_advance": { "total": 5139.680848886666, "count": 646127, "self": 41.696486964356154, "children": { "process_trajectory": { "total": 1118.7872105536517, "count": 646127, "self": 1117.3099692627438, "children": { "RLTrainer._checkpoint": { "total": 1.4772412909078412, "count": 18, "self": 1.4772412909078412 } } }, "_update_policy": { "total": 3979.1971513686585, "count": 449, "self": 445.7941814964288, "children": { "TorchPOCAOptimizer.update": { "total": 3533.4029698722297, "count": 13470, "self": 3533.4029698722297 } } } } } } }, "trainer_threads": { "total": 7.090275175869465e-07, "count": 1, "self": 7.090275175869465e-07 }, "TrainerController._save_models": { "total": 0.07875095901545137, "count": 1, "self": 0.0008666260400786996, "children": { "RLTrainer._checkpoint": { "total": 0.07788433297537267, "count": 1, "self": 0.07788433297537267 } } } } } } }