{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6196073293685913, "min": 1.6196073293685913, "max": 1.6196073293685913, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 10831.93359375, "min": 10831.93359375, "max": 10831.93359375, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.925925925925924, "min": 52.925925925925924, "max": 52.925925925925924, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 5716.0, "min": 5716.0, "max": 5716.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1521.016516083494, "min": 1521.016516083494, "max": 1521.016516083494, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 82134.89186850868, "min": 82134.89186850868, "max": 82134.89186850868, "count": 1 }, "SoccerTwos.Step.mean": { "value": 7544889.0, "min": 7544889.0, "max": 7544889.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 7544889.0, "min": 7544889.0, "max": 7544889.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.028078727424144745, "min": -0.028078727424144745, "max": -0.028078727424144745, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.4881725311279297, "min": -1.4881725311279297, "max": -1.4881725311279297, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.030530137941241264, "min": -0.030530137941241264, "max": -0.030530137941241264, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.6180973052978516, "min": -1.6180973052978516, "max": -1.6180973052978516, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11261131853427526, "min": -0.11261131853427526, "max": -0.11261131853427526, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.968399882316589, "min": -5.968399882316589, "max": -5.968399882316589, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11261131853427526, "min": -0.11261131853427526, "max": -0.11261131853427526, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.968399882316589, "min": -5.968399882316589, "max": -5.968399882316589, "count": 1 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694309186", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1694309204" }, "total": 18.141477599999998, "count": 1, "self": 0.08926389999999884, "children": { "run_training.setup": { "total": 0.1585276999999996, "count": 1, "self": 0.1585276999999996 }, "TrainerController.start_learning": { "total": 17.893686, "count": 1, "self": 0.017375300000011862, "children": { "TrainerController._reset_env": { "total": 5.037988500000001, "count": 2, "self": 5.037988500000001 }, "TrainerController.advance": { "total": 12.528668399999981, "count": 377, "self": 0.014363899999960239, "children": { "env_step": { "total": 9.479446400000006, "count": 377, "self": 7.023474400000003, "children": { "SubprocessEnvManager._take_step": { "total": 2.448307199999986, "count": 377, "self": 0.08237930000001548, "children": { "TorchPolicy.evaluate": { "total": 2.3659278999999707, "count": 686, "self": 2.3659278999999707 } } }, "workers": { "total": 0.0076648000000165695, "count": 377, "self": 0.0, "children": { "worker_root": { "total": 12.690685499999999, "count": 377, "is_parallel": true, "self": 7.292277399999977, "children": { "steps_from_proto": { "total": 0.005625900000000961, "count": 4, "is_parallel": true, "self": 0.0012017000000019706, "children": { "_process_rank_one_or_two_observation": { "total": 0.00442419999999899, "count": 16, "is_parallel": true, "self": 0.00442419999999899 } } }, "UnityEnvironment.step": { "total": 5.392782200000021, "count": 377, "is_parallel": true, "self": 0.2729520000000365, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2915378000000004, "count": 377, "is_parallel": true, "self": 0.2915378000000004 }, "communicator.exchange": { "total": 3.9169518000000068, "count": 377, "is_parallel": true, "self": 3.9169518000000068 }, "steps_from_proto": { "total": 0.9113405999999777, "count": 754, "is_parallel": true, "self": 0.2103195999999503, "children": { "_process_rank_one_or_two_observation": { "total": 0.7010210000000274, "count": 3016, "is_parallel": true, "self": 0.7010210000000274 } } } } } } } } } } }, "trainer_advance": { "total": 3.034858100000015, "count": 377, "self": 0.07185500000004552, "children": { "process_trajectory": { "total": 2.9630030999999697, "count": 377, "self": 2.9630030999999697 } } } } }, "trainer_threads": { "total": 1.900000000887303e-06, "count": 1, "self": 1.900000000887303e-06 }, "TrainerController._save_models": { "total": 0.3096519000000022, "count": 1, "self": 0.0176764000000027, "children": { "RLTrainer._checkpoint": { "total": 0.2919754999999995, "count": 1, "self": 0.2919754999999995 } } } } } } }