{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.079524040222168, "min": 2.849503517150879, "max": 3.295732021331787, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41388.8046875, "min": 23866.701171875, "max": 136343.890625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 610.25, "min": 340.57142857142856, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19528.0, "min": 15488.0, "max": 24488.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1213.3202764236314, "min": 1183.4300731029982, "max": 1214.3127574770058, "count": 252 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12133.202764236314, "min": 2366.8601462059964, "max": 28965.47585143405, "count": 252 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9260.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9260.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012774682603776455, "min": -0.030601495876908302, "max": 0.09433490037918091, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.19162024557590485, "min": -0.6442781090736389, "max": 1.226321816444397, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012120088562369347, "min": -0.02709207683801651, "max": 0.09435472637414932, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.18180133402347565, "min": -0.6449013948440552, "max": 1.2265359163284302, "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": -0.3944266666968664, "min": -0.5689750015735626, "max": 0.3378666639328003, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.916400000452995, "min": -13.843200087547302, "max": 5.153999924659729, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3944266666968664, "min": -0.5689750015735626, "max": 0.3378666639328003, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.916400000452995, "min": -13.843200087547302, "max": 5.153999924659729, "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": 0.015376377063027273, "min": 0.010229829782232022, "max": 0.02374292616150342, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015376377063027273, "min": 0.010229829782232022, "max": 0.02374292616150342, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.009417497770239909, "min": 4.064473072181348e-08, "max": 0.013197275747855505, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.009417497770239909, "min": 4.064473072181348e-08, "max": 0.013197275747855505, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.010372263782968124, "min": 4.8331188414370746e-08, "max": 0.013758951363464196, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.010372263782968124, "min": 4.8331188414370746e-08, "max": 0.013758951363464196, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714732654", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/elisa/Progetti/AI/006_SelfPlay/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwosss --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714740032" }, "total": 7378.780638908, "count": 1, "self": 10.00458656399951, "children": { "run_training.setup": { "total": 0.015399726999930863, "count": 1, "self": 0.015399726999930863 }, "TrainerController.start_learning": { "total": 7368.760652617, "count": 1, "self": 4.401767240277877, "children": { "TrainerController._reset_env": { "total": 4.277776612998423, "count": 25, "self": 4.277776612998423 }, "TrainerController.advance": { "total": 7359.879946816724, "count": 325004, "self": 4.950757543738291, "children": { "env_step": { "total": 6010.550840244123, "count": 325004, "self": 3660.7370432444677, "children": { "SubprocessEnvManager._take_step": { "total": 2346.3338186950505, "count": 325004, "self": 30.49359471477601, "children": { "TorchPolicy.evaluate": { "total": 2315.8402239802745, "count": 645236, "self": 2315.8402239802745 } } }, "workers": { "total": 3.4799783046046286, "count": 325004, "self": 0.0, "children": { "worker_root": { "total": 7359.841822465402, "count": 325004, "is_parallel": true, "self": 4198.721953494401, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025091240004257997, "count": 2, "is_parallel": true, "self": 0.0007227200012493995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017864039991764002, "count": 8, "is_parallel": true, "self": 0.0017864039991764002 } } }, "UnityEnvironment.step": { "total": 0.026724215000285767, "count": 1, "is_parallel": true, "self": 0.00045501099975808756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042476900034671417, "count": 1, "is_parallel": true, "self": 0.00042476900034671417 }, "communicator.exchange": { "total": 0.02460446100030822, "count": 1, "is_parallel": true, "self": 0.02460446100030822 }, "steps_from_proto": { "total": 0.0012399739998727455, "count": 2, "is_parallel": true, "self": 0.0002657609984453302, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009742130014274153, "count": 8, "is_parallel": true, "self": 0.0009742130014274153 } } } } } } }, "UnityEnvironment.step": { "total": 3161.097335874004, "count": 325003, "is_parallel": true, "self": 98.50350481242094, "children": { "UnityEnvironment._generate_step_input": { "total": 59.91805322097298, "count": 325003, "is_parallel": true, "self": 59.91805322097298 }, "communicator.exchange": { "total": 2719.5106338343603, "count": 325003, "is_parallel": true, "self": 2719.5106338343603 }, "steps_from_proto": { "total": 283.16514400624965, "count": 650006, "is_parallel": true, "self": 58.240512723049505, "children": { "_process_rank_one_or_two_observation": { "total": 224.92463128320014, "count": 2600024, "is_parallel": true, "self": 224.92463128320014 } } } } }, "steps_from_proto": { "total": 0.022533096997904067, "count": 48, "is_parallel": true, "self": 0.004749628981699061, "children": { "_process_rank_one_or_two_observation": { "total": 0.017783468016205006, "count": 192, "is_parallel": true, "self": 0.017783468016205006 } } } } } } } } }, "trainer_advance": { "total": 1344.3783490288633, "count": 325004, "self": 39.475215089822996, "children": { "process_trajectory": { "total": 445.65911349805174, "count": 325004, "self": 443.84921990005114, "children": { "RLTrainer._checkpoint": { "total": 1.809893598000599, "count": 10, "self": 1.809893598000599 } } }, "_update_policy": { "total": 859.2440204409886, "count": 231, "self": 303.62010625597213, "children": { "TorchPOCAOptimizer.update": { "total": 555.6239141850165, "count": 6939, "self": 555.6239141850165 } } } } } } }, "trainer_threads": { "total": 5.229994712863117e-07, "count": 1, "self": 5.229994712863117e-07 }, "TrainerController._save_models": { "total": 0.2011614240000199, "count": 1, "self": 0.0022945340006117476, "children": { "RLTrainer._checkpoint": { "total": 0.19886688999940816, "count": 1, "self": 0.19886688999940816 } } } } } } }