{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1875576972961426, "min": 2.144973039627075, "max": 2.2713446617126465, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45571.203125, "min": 34911.1328125, "max": 50452.00390625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.14285714285714, "min": 55.79545454545455, "max": 105.46808510638297, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 19072.0, "max": 20416.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1475.7673077529762, "min": 1455.5852748018806, "max": 1495.4709782409363, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 206607.42308541667, "min": 138573.4318195411, "max": 258146.97528522566, "count": 100 }, "SoccerTwos.Step.mean": { "value": 4999989.0, "min": 4009955.0, "max": 4999989.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 4999989.0, "min": 4009955.0, "max": 4999989.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008360597304999828, "min": -0.13213926553726196, "max": 0.047096967697143555, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.1704835891723633, "min": -19.013656616210938, "max": 6.358090400695801, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.005427720490843058, "min": -0.13081811368465424, "max": 0.04446444660425186, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7598809003829956, "min": -19.144575119018555, "max": 6.002700328826904, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07113428797040666, "min": -0.37446071580052376, "max": 0.30961999893188474, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 9.958800315856934, "min": -41.93960016965866, "max": 37.15439987182617, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07113428797040666, "min": -0.37446071580052376, "max": 0.30961999893188474, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 9.958800315856934, "min": -41.93960016965866, "max": 37.15439987182617, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.024346959691805146, "min": 0.020130672054559304, "max": 0.030631732359567346, "count": 96 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.024346959691805146, "min": 0.020130672054559304, "max": 0.030631732359567346, "count": 96 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08962117247283459, "min": 0.06291260526825984, "max": 0.1022199623286724, "count": 96 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08962117247283459, "min": 0.06291260526825984, "max": 0.1022199623286724, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09580556737879913, "min": 0.06390505886326234, "max": 0.10687999129295349, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09580556737879913, "min": 0.06390505886326234, "max": 0.10687999129295349, "count": 96 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 96 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 96 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 96 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 96 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 96 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 96 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718354770", "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": "1718357413" }, "total": 2643.438411529, "count": 1, "self": 0.44061282700022275, "children": { "run_training.setup": { "total": 0.05524954800000614, "count": 1, "self": 0.05524954800000614 }, "TrainerController.start_learning": { "total": 2642.9425491539996, "count": 1, "self": 1.7481662440723085, "children": { "TrainerController._reset_env": { "total": 3.148299596000129, "count": 6, "self": 3.148299596000129 }, "TrainerController.advance": { "total": 2637.7337122209274, "count": 67963, "self": 1.899848016994838, "children": { "env_step": { "total": 1835.5979456299804, "count": 67963, "self": 1395.1376912010285, "children": { "SubprocessEnvManager._take_step": { "total": 439.4613840100016, "count": 67963, "self": 11.93888216498624, "children": { "TorchPolicy.evaluate": { "total": 427.52250184501537, "count": 125514, "self": 427.52250184501537 } } }, "workers": { "total": 0.9988704189502755, "count": 67963, "self": 0.0, "children": { "worker_root": { "total": 2638.251060065022, "count": 67963, "is_parallel": true, "self": 1467.0694028729831, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007002816000010625, "count": 2, "is_parallel": true, "self": 0.0037053229999628456, "children": { "_process_rank_one_or_two_observation": { "total": 0.00329749300004778, "count": 8, "is_parallel": true, "self": 0.00329749300004778 } } }, "UnityEnvironment.step": { "total": 0.042755231000001004, "count": 1, "is_parallel": true, "self": 0.0011683379999567478, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008768920000079561, "count": 1, "is_parallel": true, "self": 0.0008768920000079561 }, "communicator.exchange": { "total": 0.037155740999992304, "count": 1, "is_parallel": true, "self": 0.037155740999992304 }, "steps_from_proto": { "total": 0.003554260000043996, "count": 2, "is_parallel": true, "self": 0.0006907179999871005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028635420000568956, "count": 8, "is_parallel": true, "self": 0.0028635420000568956 } } } } } } }, "steps_from_proto": { "total": 0.010347326000214707, "count": 10, "is_parallel": true, "self": 0.0023058779999587387, "children": { "_process_rank_one_or_two_observation": { "total": 0.008041448000255969, "count": 40, "is_parallel": true, "self": 0.008041448000255969 } } }, "UnityEnvironment.step": { "total": 1171.1713098660387, "count": 67962, "is_parallel": true, "self": 72.15924076098236, "children": { "UnityEnvironment._generate_step_input": { "total": 50.23150113503095, "count": 67962, "is_parallel": true, "self": 50.23150113503095 }, "communicator.exchange": { "total": 815.8509057829692, "count": 67962, "is_parallel": true, "self": 815.8509057829692 }, "steps_from_proto": { "total": 232.92966218705607, "count": 135924, "is_parallel": true, "self": 39.79592852296594, "children": { "_process_rank_one_or_two_observation": { "total": 193.13373366409013, "count": 543696, "is_parallel": true, "self": 193.13373366409013 } } } } } } } } } } }, "trainer_advance": { "total": 800.2359185739523, "count": 67963, "self": 13.141391972977772, "children": { "process_trajectory": { "total": 223.8453884169735, "count": 67963, "self": 223.12084548197345, "children": { "RLTrainer._checkpoint": { "total": 0.724542935000045, "count": 2, "self": 0.724542935000045 } } }, "_update_policy": { "total": 563.249138184001, "count": 96, "self": 308.2580305080081, "children": { "TorchPOCAOptimizer.update": { "total": 254.9911076759929, "count": 5760, "self": 254.9911076759929 } } } } } } }, "trainer_threads": { "total": 1.0160001693293452e-06, "count": 1, "self": 1.0160001693293452e-06 }, "TrainerController._save_models": { "total": 0.3123700769997413, "count": 1, "self": 0.004324635999637394, "children": { "RLTrainer._checkpoint": { "total": 0.3080454410001039, "count": 1, "self": 0.3080454410001039 } } } } } } }