{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.252471685409546, "min": 2.247462749481201, "max": 3.295745372772217, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 223733.515625, "min": 223733.515625, "max": 343390.3125, "count": 100 }, "SoccerTwos.Step.mean": { "value": 4999984.0, "min": 49982.0, "max": 4999984.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 4999984.0, "min": 49982.0, "max": 4999984.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.020266307517886162, "min": -0.057345956563949585, "max": 0.13314105570316315, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 18.219409942626953, "min": -46.2781867980957, "max": 101.05406188964844, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014914730563759804, "min": -0.060067735612392426, "max": 0.13315565884113312, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 13.408342361450195, "min": -48.47466278076172, "max": 101.06513977050781, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.56444444444445, "min": 54.56444444444445, "max": 913.6206896551724, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 98216.0, "min": 88412.0, "max": 106144.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1598.2112819853585, "min": 1191.5892503730151, "max": 1598.2112819853585, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 1438390.1537868227, "min": 7196.60211581334, "max": 1438390.1537868227, "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": -0.04989543945028201, "min": -0.2776871807276247, "max": 0.20659459503115835, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -44.85600006580353, "min": -110.22019970417023, "max": 136.89319968223572, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04989543945028201, "min": -0.2776871807276247, "max": 0.20659459503115835, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -44.85600006580353, "min": -110.22019970417023, "max": 136.89319968223572, "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": 0.07025541723061723, "min": 0.06170361926076741, "max": 0.07404013842808059, "count": 99 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.07025541723061723, "min": 0.06170361926076741, "max": 0.07404013842808059, "count": 99 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.066931084660656, "min": 0.0007612304182455571, "max": 0.07150022778660059, "count": 99 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.066931084660656, "min": 0.0007612304182455571, "max": 0.07150022778660059, "count": 99 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08256172361162008, "min": 0.0007654172855720204, "max": 0.08760003953471653, "count": 99 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08256172361162008, "min": 0.0007654172855720204, "max": 0.08760003953471653, "count": 99 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00020000000000000004, "min": 0.00020000000000000004, "max": 0.00020000000000000006, "count": 99 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00020000000000000004, "min": 0.00020000000000000004, "max": 0.00020000000000000006, "count": 99 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999998, "min": 0.19999999999999998, "max": 0.19999999999999998, "count": 99 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999998, "min": 0.19999999999999998, "max": 0.19999999999999998, "count": 99 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.004999999999999999, "max": 0.005, "count": 99 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.004999999999999999, "max": 0.005, "count": 99 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679845740", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\lloyd\\anaconda3\\envs\\newrl\\Scripts\\mlagents-learn C:/Users/lloyd/Documents/Online Courses/HuggingFace_RL_Course/ml-agents-aivsai/config/poca/SoccerTwos.yaml --env=C:/Users/lloyd/Documents/Online Courses/HuggingFace_RL_Course/ml-agents-aivsai/ml-agents/mlagents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679891987" }, "total": 46246.4514343, "count": 1, "self": 2.9367651999928057, "children": { "run_training.setup": { "total": 0.36043800000000026, "count": 1, "self": 0.36043800000000026 }, "TrainerController.start_learning": { "total": 46243.1542311, "count": 1, "self": 14.655313696952362, "children": { "TrainerController._reset_env": { "total": 10.143202400009947, "count": 10, "self": 10.143202400009947 }, "TrainerController.advance": { "total": 46218.08220800304, "count": 331723, "self": 16.456694704502297, "children": { "env_step": { "total": 11683.669627898968, "count": 331723, "self": 9156.40845329973, "children": { "SubprocessEnvManager._take_step": { "total": 2517.8269674997714, "count": 331723, "self": 102.43432869865319, "children": { "TorchPolicy.evaluate": { "total": 2415.392638801118, "count": 626278, "self": 2415.392638801118 } } }, "workers": { "total": 9.434207099466143, "count": 331723, "self": 0.0, "children": { "worker_root": { "total": 46210.529652598, "count": 331723, "is_parallel": true, "self": 38920.10547450003, "children": { "steps_from_proto": { "total": 0.033488999991286406, "count": 20, "is_parallel": true, "self": 0.007584099987790083, "children": { "_process_rank_one_or_two_observation": { "total": 0.025904900003496323, "count": 80, "is_parallel": true, "self": 0.025904900003496323 } } }, "UnityEnvironment.step": { "total": 7290.390689097977, "count": 331723, "is_parallel": true, "self": 400.75590359949183, "children": { "UnityEnvironment._generate_step_input": { "total": 369.65095569798314, "count": 331723, "is_parallel": true, "self": 369.65095569798314 }, "communicator.exchange": { "total": 5196.90245500056, "count": 331723, "is_parallel": true, "self": 5196.90245500056 }, "steps_from_proto": { "total": 1323.0813747999414, "count": 663446, "is_parallel": true, "self": 271.62063830317516, "children": { "_process_rank_one_or_two_observation": { "total": 1051.4607364967662, "count": 2653784, "is_parallel": true, "self": 1051.4607364967662 } } } } } } } } } } }, "trainer_advance": { "total": 34517.95588539957, "count": 331723, "self": 97.06072600073821, "children": { "process_trajectory": { "total": 8085.356377398843, "count": 331723, "self": 8057.349834998906, "children": { "RLTrainer._checkpoint": { "total": 28.006542399936478, "count": 100, "self": 28.006542399936478 } } }, "_update_policy": { "total": 26335.53878199999, "count": 99, "self": 1468.4913752005632, "children": { "TorchPOCAOptimizer.update": { "total": 24867.047406799426, "count": 116259, "self": 24867.047406799426 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.27350599999772385, "count": 1, "self": 0.008825599994452205, "children": { "RLTrainer._checkpoint": { "total": 0.26468040000327164, "count": 1, "self": 0.26468040000327164 } } } } } } }