{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.062716484069824, "min": 2.062716484069824, "max": 3.295754909515381, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40594.26171875, "min": 18994.7890625, "max": 105825.15625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.46835443037975, "min": 42.577586206896555, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19740.0, "min": 16276.0, "max": 23484.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1564.2181875760673, "min": 1198.3671901743817, "max": 1564.8541732117374, "count": 476 }, "SoccerTwos.Self-play.ELO.sum": { "value": 247146.47363701864, "min": 2401.1547534115844, "max": 355729.74307257077, "count": 476 }, "SoccerTwos.Step.mean": { "value": 4999950.0, "min": 9870.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999950.0, "min": 9870.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06773501634597778, "min": -0.09971068799495697, "max": 0.24734550714492798, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.769867897033691, "min": -14.09639835357666, "max": 48.72706604003906, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06862561404705048, "min": -0.10212115943431854, "max": 0.25609320402145386, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.91147232055664, "min": -14.348769187927246, "max": 50.45036315917969, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3046327034632365, "min": -0.5856881363917206, "max": 0.5983666628599167, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -48.4365998506546, "min": -48.4365998506546, "max": 104.700399518013, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3046327034632365, "min": -0.5856881363917206, "max": 0.5983666628599167, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -48.4365998506546, "min": -48.4365998506546, "max": 104.700399518013, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018281979297504827, "min": 0.010130076021838855, "max": 0.023477463375699396, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018281979297504827, "min": 0.010130076021838855, "max": 0.023477463375699396, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09845783586303393, "min": 5.352624725674104e-06, "max": 0.10853384161988894, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09845783586303393, "min": 5.352624725674104e-06, "max": 0.10853384161988894, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10088658804694811, "min": 6.464888360824261e-06, "max": 0.11159325142701466, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10088658804694811, "min": 6.464888360824261e-06, "max": 0.11159325142701466, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675335391", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675351148" }, "total": 15756.8323666, "count": 1, "self": 0.41181610000057844, "children": { "run_training.setup": { "total": 0.09209000000000067, "count": 1, "self": 0.09209000000000067 }, "TrainerController.start_learning": { "total": 15756.328460499999, "count": 1, "self": 8.451669299813148, "children": { "TrainerController._reset_env": { "total": 7.523006699998934, "count": 25, "self": 7.523006699998934 }, "TrainerController.advance": { "total": 15740.242395900186, "count": 337581, "self": 8.33220730069661, "children": { "env_step": { "total": 6436.712357899581, "count": 337581, "self": 5166.438548599402, "children": { "SubprocessEnvManager._take_step": { "total": 1264.6939993004273, "count": 337581, "self": 44.46117310012937, "children": { "TorchPolicy.evaluate": { "total": 1220.232826200298, "count": 633318, "self": 1220.232826200298 } } }, "workers": { "total": 5.579809999751621, "count": 337581, "self": 0.0, "children": { "worker_root": { "total": 15739.011112700086, "count": 337581, "is_parallel": true, "self": 11583.964069900314, "children": { "steps_from_proto": { "total": 0.04538339999643437, "count": 50, "is_parallel": true, "self": 0.010079899990840246, "children": { "_process_rank_one_or_two_observation": { "total": 0.035303500005594124, "count": 200, "is_parallel": true, "self": 0.035303500005594124 } } }, "UnityEnvironment.step": { "total": 4155.001659399775, "count": 337581, "is_parallel": true, "self": 197.2867014000999, "children": { "UnityEnvironment._generate_step_input": { "total": 159.4818111002687, "count": 337581, "is_parallel": true, "self": 159.4818111002687 }, "communicator.exchange": { "total": 3257.5309167999226, "count": 337581, "is_parallel": true, "self": 3257.5309167999226 }, "steps_from_proto": { "total": 540.702230099484, "count": 675162, "is_parallel": true, "self": 120.56313259936962, "children": { "_process_rank_one_or_two_observation": { "total": 420.1390975001144, "count": 2700648, "is_parallel": true, "self": 420.1390975001144 } } } } } } } } } } }, "trainer_advance": { "total": 9295.197830699908, "count": 337581, "self": 58.21511770005418, "children": { "process_trajectory": { "total": 1378.5219130998507, "count": 337581, "self": 1377.1326900998522, "children": { "RLTrainer._checkpoint": { "total": 1.3892229999985375, "count": 10, "self": 1.3892229999985375 } } }, "_update_policy": { "total": 7858.460799900004, "count": 239, "self": 961.5346561999231, "children": { "TorchPOCAOptimizer.update": { "total": 6896.9261437000805, "count": 7170, "self": 6896.9261437000805 } } } } } } }, "trainer_threads": { "total": 8.000006346264854e-07, "count": 1, "self": 8.000006346264854e-07 }, "TrainerController._save_models": { "total": 0.11138779999964754, "count": 1, "self": 0.0026569000001472887, "children": { "RLTrainer._checkpoint": { "total": 0.10873089999950025, "count": 1, "self": 0.10873089999950025 } } } } } } }