{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3965755701065063, "min": 1.2941997051239014, "max": 3.2957096099853516, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29450.984375, "min": 22217.34765625, "max": 105462.6640625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.78571428571429, "min": 38.5703125, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19820.0, "min": 16032.0, "max": 24644.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1563.1523146601005, "min": 1199.9395198905781, "max": 1651.3518033802509, "count": 4998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 218841.32405241407, "min": 2401.785197241094, "max": 383847.59471347474, "count": 4998 }, "SoccerTwos.Step.mean": { "value": 49999937.0, "min": 9342.0, "max": 49999937.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999937.0, "min": 9342.0, "max": 49999937.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.002657536184415221, "min": -0.14241209626197815, "max": 0.13732264935970306, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.3720550537109375, "min": -26.68775749206543, "max": 27.782060623168945, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0032018115743994713, "min": -0.14282353222370148, "max": 0.13515380024909973, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4482536315917969, "min": -26.44363784790039, "max": 27.906963348388672, "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": -0.138899998153959, "min": -0.5, "max": 0.4004842105664705, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.44599974155426, "min": -65.53640019893646, "max": 69.17319959402084, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.138899998153959, "min": -0.5, "max": 0.4004842105664705, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.44599974155426, "min": -65.53640019893646, "max": 69.17319959402084, "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": 0.015663005656097084, "min": 0.00953428414359223, "max": 0.02628656509332359, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015663005656097084, "min": 0.00953428414359223, "max": 0.02628656509332359, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08575780043999354, "min": 0.0008426467737687441, "max": 0.12882075359423956, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08575780043999354, "min": 0.0008426467737687441, "max": 0.12882075359423956, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08644222045938174, "min": 0.0010219749790849164, "max": 0.13156426896651585, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08644222045938174, "min": 0.0010219749790849164, "max": 0.13156426896651585, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727022714", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/luyang/miniconda3/envs/unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos --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+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727099780" }, "total": 77065.63031259691, "count": 1, "self": 0.2690465848427266, "children": { "run_training.setup": { "total": 0.01654282188974321, "count": 1, "self": 0.01654282188974321 }, "TrainerController.start_learning": { "total": 77065.34472319018, "count": 1, "self": 41.992008559871465, "children": { "TrainerController._reset_env": { "total": 5.6184677623678, "count": 250, "self": 5.6184677623678 }, "TrainerController.advance": { "total": 77017.55734310276, "count": 3455783, "self": 43.921300541609526, "children": { "env_step": { "total": 61839.30751401652, "count": 3455783, "self": 47876.72523483215, "children": { "SubprocessEnvManager._take_step": { "total": 13935.756036157254, "count": 3455783, "self": 301.245095273247, "children": { "TorchPolicy.evaluate": { "total": 13634.510940884007, "count": 6277986, "self": 13634.510940884007 } } }, "workers": { "total": 26.826243027113378, "count": 3455783, "self": 0.0, "children": { "worker_root": { "total": 76982.57255199621, "count": 3455783, "is_parallel": true, "self": 35087.05407837918, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001981878885999322, "count": 2, "is_parallel": true, "self": 0.0004987514112144709, "children": { "_process_rank_one_or_two_observation": { "total": 0.001483127474784851, "count": 8, "is_parallel": true, "self": 0.001483127474784851 } } }, "UnityEnvironment.step": { "total": 0.02064413600601256, "count": 1, "is_parallel": true, "self": 0.000515002990141511, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042328890413045883, "count": 1, "is_parallel": true, "self": 0.00042328890413045883 }, "communicator.exchange": { "total": 0.018088181037455797, "count": 1, "is_parallel": true, "self": 0.018088181037455797 }, "steps_from_proto": { "total": 0.001617663074284792, "count": 2, "is_parallel": true, "self": 0.00031321472488343716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013044483494013548, "count": 8, "is_parallel": true, "self": 0.0013044483494013548 } } } } } } }, "UnityEnvironment.step": { "total": 41894.99184828624, "count": 3455782, "is_parallel": true, "self": 1616.9232284147292, "children": { "UnityEnvironment._generate_step_input": { "total": 1053.0702304758597, "count": 3455782, "is_parallel": true, "self": 1053.0702304758597 }, "communicator.exchange": { "total": 34210.672145488206, "count": 3455782, "is_parallel": true, "self": 34210.672145488206 }, "steps_from_proto": { "total": 5014.326243907446, "count": 6911564, "is_parallel": true, "self": 913.8798143102322, "children": { "_process_rank_one_or_two_observation": { "total": 4100.446429597214, "count": 27646256, "is_parallel": true, "self": 4100.446429597214 } } } } }, "steps_from_proto": { "total": 0.52662533079274, "count": 498, "is_parallel": true, "self": 0.09680508123710752, "children": { "_process_rank_one_or_two_observation": { "total": 0.42982024955563247, "count": 1992, "is_parallel": true, "self": 0.42982024955563247 } } } } } } } } }, "trainer_advance": { "total": 15134.328528544633, "count": 3455783, "self": 340.7303969603963, "children": { "process_trajectory": { "total": 7778.258538229857, "count": 3455783, "self": 7760.871574743651, "children": { "RLTrainer._checkpoint": { "total": 17.386963486205786, "count": 100, "self": 17.386963486205786 } } }, "_update_policy": { "total": 7015.33959335438, "count": 2425, "self": 4584.478945414536, "children": { "TorchPOCAOptimizer.update": { "total": 2430.860647939844, "count": 72750, "self": 2430.860647939844 } } } } } } }, "trainer_threads": { "total": 7.799826562404633e-07, "count": 1, "self": 7.799826562404633e-07 }, "TrainerController._save_models": { "total": 0.1769029852002859, "count": 1, "self": 0.0015590942930430174, "children": { "RLTrainer._checkpoint": { "total": 0.1753438909072429, "count": 1, "self": 0.1753438909072429 } } } } } } }