{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.181635618209839, "min": 3.1310319900512695, "max": 3.295783042907715, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 59967.46875, "min": 15476.576171875, "max": 129763.7890625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 844.6666666666666, "min": 379.4166666666667, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20272.0, "min": 8088.0, "max": 28120.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1205.6007877300565, "min": 1197.9794261740456, "max": 1206.847257571617, "count": 74 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4822.403150920226, "min": 2395.958852348091, "max": 12019.931544315958, "count": 74 }, "SoccerTwos.Step.mean": { "value": 999140.0, "min": 9076.0, "max": 999140.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999140.0, "min": 9076.0, "max": 999140.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00730251194909215, "min": -0.013627061620354652, "max": 0.011445614509284496, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.08032763004302979, "min": -0.21750321984291077, "max": 0.20602105557918549, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00721974391490221, "min": -0.013208143413066864, "max": 0.012260202318429947, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.07941718399524689, "min": -0.2169845700263977, "max": 0.22068363428115845, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.36363636363636365, "min": -0.4, "max": 0.2946461576681871, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0, "min": -4.0, "max": 3.830400049686432, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.36363636363636365, "min": -0.4, "max": 0.2946461576681871, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0, "min": -4.0, "max": 3.830400049686432, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012284514179918915, "min": 0.01193332662708902, "max": 0.022588042030110955, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012284514179918915, "min": 0.01193332662708902, "max": 0.022588042030110955, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002764144043127696, "min": 1.374463268651501e-06, "max": 0.006254609518994887, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002764144043127696, "min": 1.374463268651501e-06, "max": 0.006254609518994887, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0027654607547447085, "min": 1.5665934048077664e-06, "max": 0.006314095466708144, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0027654607547447085, "min": 1.5665934048077664e-06, "max": 0.006314095466708144, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681667941", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/maurizio/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos_v3 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681674261" }, "total": 6320.1638132849985, "count": 1, "self": 0.3275492629982182, "children": { "run_training.setup": { "total": 0.020235527998011094, "count": 1, "self": 0.020235527998011094 }, "TrainerController.start_learning": { "total": 6319.816028494002, "count": 1, "self": 1.6746884334716015, "children": { "TrainerController._reset_env": { "total": 2.4075916079964372, "count": 10, "self": 2.4075916079964372 }, "TrainerController.advance": { "total": 6315.529840422525, "count": 67676, "self": 2.1853923139642575, "children": { "env_step": { "total": 5231.5781633375445, "count": 67676, "self": 4990.9453469912405, "children": { "SubprocessEnvManager._take_step": { "total": 239.44919070931792, "count": 67676, "self": 10.813114023330854, "children": { "TorchPolicy.evaluate": { "total": 228.63607668598706, "count": 134390, "self": 228.63607668598706 } } }, "workers": { "total": 1.1836256369861076, "count": 67676, "self": 0.0, "children": { "worker_root": { "total": 6315.309357035003, "count": 67676, "is_parallel": true, "self": 1527.7998311849733, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003449397008807864, "count": 2, "is_parallel": true, "self": 0.0007527170091634616, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026966799996444024, "count": 8, "is_parallel": true, "self": 0.0026966799996444024 } } }, "UnityEnvironment.step": { "total": 0.0818850859941449, "count": 1, "is_parallel": true, "self": 0.00040592400182504207, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012932449972140603, "count": 1, "is_parallel": true, "self": 0.0012932449972140603 }, "communicator.exchange": { "total": 0.07591495699307416, "count": 1, "is_parallel": true, "self": 0.07591495699307416 }, "steps_from_proto": { "total": 0.004270960002031643, "count": 2, "is_parallel": true, "self": 0.0006618689876631834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036090910143684596, "count": 8, "is_parallel": true, "self": 0.0036090910143684596 } } } } } } }, "UnityEnvironment.step": { "total": 4787.490800264022, "count": 67675, "is_parallel": true, "self": 16.627890948948334, "children": { "UnityEnvironment._generate_step_input": { "total": 99.02636314854317, "count": 67675, "is_parallel": true, "self": 99.02636314854317 }, "communicator.exchange": { "total": 4500.120211521702, "count": 67675, "is_parallel": true, "self": 4500.120211521702 }, "steps_from_proto": { "total": 171.71633464482875, "count": 135350, "is_parallel": true, "self": 25.875414865739003, "children": { "_process_rank_one_or_two_observation": { "total": 145.84091977908975, "count": 541400, "is_parallel": true, "self": 145.84091977908975 } } } } }, "steps_from_proto": { "total": 0.018725586007349193, "count": 18, "is_parallel": true, "self": 0.002912106974690687, "children": { "_process_rank_one_or_two_observation": { "total": 0.015813479032658506, "count": 72, "is_parallel": true, "self": 0.015813479032658506 } } } } } } } } }, "trainer_advance": { "total": 1081.7662847710162, "count": 67676, "self": 13.833539977873443, "children": { "process_trajectory": { "total": 156.12275255315035, "count": 67676, "self": 155.71780656214833, "children": { "RLTrainer._checkpoint": { "total": 0.4049459910020232, "count": 2, "self": 0.4049459910020232 } } }, "_update_policy": { "total": 911.8099922399924, "count": 46, "self": 133.3887808538857, "children": { "TorchPOCAOptimizer.update": { "total": 778.4212113861067, "count": 1389, "self": 778.4212113861067 } } } } } } }, "trainer_threads": { "total": 6.020054570399225e-07, "count": 1, "self": 6.020054570399225e-07 }, "TrainerController._save_models": { "total": 0.20390742800373118, "count": 1, "self": 0.013858853999408893, "children": { "RLTrainer._checkpoint": { "total": 0.1900485740043223, "count": 1, "self": 0.1900485740043223 } } } } } } }