{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4201643466949463, "min": 1.3760290145874023, "max": 3.29569673538208, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27539.826171875, "min": 17013.634765625, "max": 108446.1484375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 76.06060606060606, "min": 44.554545454545455, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20080.0, "min": 11908.0, "max": 30344.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1559.4187701124695, "min": 1182.2200895003532, "max": 1669.8784838732513, "count": 4939 }, "SoccerTwos.Self-play.ELO.sum": { "value": 205843.27765484597, "min": 2364.4401790007064, "max": 341754.7593396053, "count": 4939 }, "SoccerTwos.Step.mean": { "value": 49999952.0, "min": 9188.0, "max": 49999952.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999952.0, "min": 9188.0, "max": 49999952.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01004683319479227, "min": -0.1283930093050003, "max": 0.1464795172214508, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.336228847503662, "min": -22.826171875, "max": 24.555360794067383, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009106192737817764, "min": -0.129206120967865, "max": 0.14550182223320007, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.2111235857009888, "min": -22.42377471923828, "max": 25.301570892333984, "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": -0.12639699304910532, "min": -0.6666666666666666, "max": 0.5480761868613107, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.810800075531006, "min": -64.7603999376297, "max": 59.623199701309204, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12639699304910532, "min": -0.6666666666666666, "max": 0.5480761868613107, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.810800075531006, "min": -64.7603999376297, "max": 59.623199701309204, "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": 0.018519588883888598, "min": 0.009680798851574461, "max": 0.025912521505961194, "count": 2420 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018519588883888598, "min": 0.009680798851574461, "max": 0.025912521505961194, "count": 2420 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0942157323161761, "min": 6.27514643269933e-07, "max": 0.11612870022654534, "count": 2420 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0942157323161761, "min": 6.27514643269933e-07, "max": 0.11612870022654534, "count": 2420 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09627160876989364, "min": 5.592775825865222e-07, "max": 0.11845562209685644, "count": 2420 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09627160876989364, "min": 5.592775825865222e-07, "max": 0.11845562209685644, "count": 2420 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2420 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2420 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2420 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2420 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2420 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2420 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729338261", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\yongkseo\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1729419756" }, "total": 81493.7608779, "count": 1, "self": 0.3364776999951573, "children": { "run_training.setup": { "total": 0.13590059999842197, "count": 1, "self": 0.13590059999842197 }, "TrainerController.start_learning": { "total": 81493.2884996, "count": 1, "self": 53.013638499207445, "children": { "TrainerController._reset_env": { "total": 6.9478357000116375, "count": 250, "self": 6.9478357000116375 }, "TrainerController.advance": { "total": 81433.24586920078, "count": 3416586, "self": 52.43847630273376, "children": { "env_step": { "total": 37983.07697930693, "count": 3416586, "self": 28740.3626186048, "children": { "SubprocessEnvManager._take_step": { "total": 9211.062967196362, "count": 3416586, "self": 318.6551877049278, "children": { "TorchPolicy.evaluate": { "total": 8892.407779491434, "count": 6287466, "self": 8892.407779491434 } } }, "workers": { "total": 31.651393505766464, "count": 3416586, "self": 0.0, "children": { "worker_root": { "total": 81421.48727009684, "count": 3416586, "is_parallel": true, "self": 58375.67622640871, "children": { "steps_from_proto": { "total": 0.27842489996692166, "count": 500, "is_parallel": true, "self": 0.05472250020829961, "children": { "_process_rank_one_or_two_observation": { "total": 0.22370239975862205, "count": 2000, "is_parallel": true, "self": 0.22370239975862205 } } }, "UnityEnvironment.step": { "total": 23045.532618788166, "count": 3416586, "is_parallel": true, "self": 1146.8519696675576, "children": { "UnityEnvironment._generate_step_input": { "total": 839.3518982041423, "count": 3416586, "is_parallel": true, "self": 839.3518982041423 }, "communicator.exchange": { "total": 17501.82970619885, "count": 3416586, "is_parallel": true, "self": 17501.82970619885 }, "steps_from_proto": { "total": 3557.499044717617, "count": 6833172, "is_parallel": true, "self": 698.6394697922588, "children": { "_process_rank_one_or_two_observation": { "total": 2858.859574925358, "count": 27332688, "is_parallel": true, "self": 2858.859574925358 } } } } } } } } } } }, "trainer_advance": { "total": 43397.73041359111, "count": 3416586, "self": 375.08932699069555, "children": { "process_trajectory": { "total": 9295.895894200694, "count": 3416586, "self": 9287.601464900763, "children": { "RLTrainer._checkpoint": { "total": 8.294429299930925, "count": 100, "self": 8.294429299930925 } } }, "_update_policy": { "total": 33726.74519239972, "count": 2420, "self": 5000.413113001428, "children": { "TorchPOCAOptimizer.update": { "total": 28726.332079398293, "count": 72600, "self": 28726.332079398293 } } } } } } }, "trainer_threads": { "total": 6.00004568696022e-07, "count": 1, "self": 6.00004568696022e-07 }, "TrainerController._save_models": { "total": 0.08115559999714606, "count": 1, "self": 0.0027892999933101237, "children": { "RLTrainer._checkpoint": { "total": 0.07836630000383593, "count": 1, "self": 0.07836630000383593 } } } } } } }