{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8641321659088135, "min": 1.7908551692962646, "max": 3.2957489490509033, "count": 509 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38594.9921875, "min": 14536.015625, "max": 136551.90625, "count": 509 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.91025641025641, "min": 41.398305084745765, "max": 999.0, "count": 509 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19940.0, "min": 13212.0, "max": 29672.0, "count": 509 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1632.8899370576994, "min": 1191.110470024826, "max": 1655.0225014802024, "count": 501 }, "SoccerTwos.Self-play.ELO.sum": { "value": 254730.8301810011, "min": 2382.220940049652, "max": 375787.27849597647, "count": 501 }, "SoccerTwos.Step.mean": { "value": 5089950.0, "min": 9854.0, "max": 5089950.0, "count": 509 }, "SoccerTwos.Step.sum": { "value": 5089950.0, "min": 9854.0, "max": 5089950.0, "count": 509 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01745498552918434, "min": -0.08539241552352905, "max": 0.21286641061306, "count": 509 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.722977638244629, "min": -16.76850700378418, "max": 29.801298141479492, "count": 509 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02577521838247776, "min": -0.09171554446220398, "max": 0.21494805812835693, "count": 509 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.020934104919434, "min": -16.529672622680664, "max": 30.092727661132812, "count": 509 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 509 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 509 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1250102542913877, "min": -0.6153846153846154, "max": 0.5182719993591308, "count": 509 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.501599669456482, "min": -51.33580005168915, "max": 64.78399991989136, "count": 509 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1250102542913877, "min": -0.6153846153846154, "max": 0.5182719993591308, "count": 509 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.501599669456482, "min": -51.33580005168915, "max": 64.78399991989136, "count": 509 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 509 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 509 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02126805322865645, "min": 0.011157380873434401, "max": 0.024535768770147116, "count": 245 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02126805322865645, "min": 0.011157380873434401, "max": 0.024535768770147116, "count": 245 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11063808078567187, "min": 0.0008122223856238028, "max": 0.1258967603246371, "count": 245 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11063808078567187, "min": 0.0008122223856238028, "max": 0.1258967603246371, "count": 245 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11299070691068967, "min": 0.0008620897366199643, "max": 0.1278861070672671, "count": 245 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11299070691068967, "min": 0.0008620897366199643, "max": 0.1278861070672671, "count": 245 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 245 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 245 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 245 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 245 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 245 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 245 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695558805", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\sanya\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos1 --no-graphics", "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": "1695573725" }, "total": 14920.2060066, "count": 1, "self": 4.154124499998943, "children": { "run_training.setup": { "total": 0.07894639999999997, "count": 1, "self": 0.07894639999999997 }, "TrainerController.start_learning": { "total": 14915.9729357, "count": 1, "self": 9.15670090049207, "children": { "TrainerController._reset_env": { "total": 3.404343799999321, "count": 26, "self": 3.404343799999321 }, "TrainerController.advance": { "total": 14903.250481099509, "count": 348115, "self": 9.189602699574607, "children": { "env_step": { "total": 6324.050142599904, "count": 348115, "self": 5052.85849279922, "children": { "SubprocessEnvManager._take_step": { "total": 1265.512111200247, "count": 348115, "self": 48.2890753008669, "children": { "TorchPolicy.evaluate": { "total": 1217.2230358993802, "count": 643006, "self": 1217.2230358993802 } } }, "workers": { "total": 5.679538600437461, "count": 348114, "self": 0.0, "children": { "worker_root": { "total": 14900.018855200271, "count": 348114, "is_parallel": true, "self": 10778.057084300364, "children": { "steps_from_proto": { "total": 0.05163909999585847, "count": 52, "is_parallel": true, "self": 0.009670500012492145, "children": { "_process_rank_one_or_two_observation": { "total": 0.04196859998336633, "count": 208, "is_parallel": true, "self": 0.04196859998336633 } } }, "UnityEnvironment.step": { "total": 4121.910131799911, "count": 348114, "is_parallel": true, "self": 215.7407381998064, "children": { "UnityEnvironment._generate_step_input": { "total": 156.97218570024103, "count": 348114, "is_parallel": true, "self": 156.97218570024103 }, "communicator.exchange": { "total": 3079.25841819985, "count": 348114, "is_parallel": true, "self": 3079.25841819985 }, "steps_from_proto": { "total": 669.9387897000138, "count": 696228, "is_parallel": true, "self": 128.10606009812727, "children": { "_process_rank_one_or_two_observation": { "total": 541.8327296018865, "count": 2784912, "is_parallel": true, "self": 541.8327296018865 } } } } } } } } } } }, "trainer_advance": { "total": 8570.010735800031, "count": 348114, "self": 64.94944539986318, "children": { "process_trajectory": { "total": 1374.2275195001607, "count": 348114, "self": 1372.68464780016, "children": { "RLTrainer._checkpoint": { "total": 1.54287170000066, "count": 10, "self": 1.54287170000066 } } }, "_update_policy": { "total": 7130.833770900007, "count": 245, "self": 726.3377767999818, "children": { "TorchPOCAOptimizer.update": { "total": 6404.495994100025, "count": 7350, "self": 6404.495994100025 } } } } } } }, "trainer_threads": { "total": 2.7999994927085936e-06, "count": 1, "self": 2.7999994927085936e-06 }, "TrainerController._save_models": { "total": 0.16140710000036051, "count": 1, "self": 0.008262199999080622, "children": { "RLTrainer._checkpoint": { "total": 0.1531449000012799, "count": 1, "self": 0.1531449000012799 } } } } } } }