{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5486077070236206, "min": 1.4257868528366089, "max": 1.659350037574768, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31616.375, "min": 24531.12890625, "max": 36951.8359375, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.54794520547945, "min": 42.56410256410256, "max": 84.71186440677967, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 18300.0, "max": 20824.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1840.0992263870494, "min": 1790.2779419253404, "max": 1870.3677281544813, "count": 1000 }, "SoccerTwos.Self-play.ELO.sum": { "value": 268654.4870525092, "min": 217117.16829232912, "max": 429375.80617991847, "count": 1000 }, "SoccerTwos.Step.mean": { "value": 29999866.0, "min": 20009970.0, "max": 29999866.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 29999866.0, "min": 20009970.0, "max": 29999866.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.045076049864292145, "min": -0.14429353177547455, "max": 0.0751807764172554, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.581103324890137, "min": -29.86876106262207, "max": 13.98057746887207, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04599927365779877, "min": -0.14564180374145508, "max": 0.07922926545143127, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.715893745422363, "min": -30.14785385131836, "max": 14.306844711303711, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1965616418890757, "min": -0.3465822011388409, "max": 0.26612805934261075, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 28.697999715805054, "min": -69.23179996013641, "max": 43.819599986076355, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1965616418890757, "min": -0.3465822011388409, "max": 0.26612805934261075, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 28.697999715805054, "min": -69.23179996013641, "max": 43.819599986076355, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02138696184071402, "min": 0.010841272244821691, "max": 0.026033086667302995, "count": 485 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02138696184071402, "min": 0.010841272244821691, "max": 0.026033086667302995, "count": 485 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10419657602906227, "min": 0.08365789850552877, "max": 0.12309435109297434, "count": 485 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10419657602906227, "min": 0.08365789850552877, "max": 0.12309435109297434, "count": 485 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10570075909296671, "min": 0.08490194454789161, "max": 0.1253761162360509, "count": 485 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10570075909296671, "min": 0.08490194454789161, "max": 0.1253761162360509, "count": 485 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 485 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 485 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 485 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 485 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 485 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 485 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675970526", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/sasha/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1676006308" }, "total": 35782.343051638, "count": 1, "self": 1.1854592410018086, "children": { "run_training.setup": { "total": 0.02808354099999999, "count": 1, "self": 0.02808354099999999 }, "TrainerController.start_learning": { "total": 35781.129508856, "count": 1, "self": 17.16976702806278, "children": { "TrainerController._reset_env": { "total": 2.8885984789992962, "count": 41, "self": 2.8885984789992962 }, "TrainerController.advance": { "total": 35760.86882777594, "count": 693848, "self": 17.35742380820011, "children": { "env_step": { "total": 10704.037458891959, "count": 693848, "self": 8661.957631522762, "children": { "SubprocessEnvManager._take_step": { "total": 2031.864475240499, "count": 693848, "self": 79.07862914951193, "children": { "TorchPolicy.evaluate": { "total": 1952.785846090987, "count": 1253574, "self": 1952.785846090987 } } }, "workers": { "total": 10.215352128697715, "count": 693848, "self": 0.0, "children": { "worker_root": { "total": 35747.55798322347, "count": 693848, "is_parallel": true, "self": 28773.72869359092, "children": { "steps_from_proto": { "total": 0.07217847300578617, "count": 82, "is_parallel": true, "self": 0.015507841014466894, "children": { "_process_rank_one_or_two_observation": { "total": 0.056670631991319276, "count": 328, "is_parallel": true, "self": 0.056670631991319276 } } }, "UnityEnvironment.step": { "total": 6973.757111159546, "count": 693848, "is_parallel": true, "self": 437.2786500562015, "children": { "UnityEnvironment._generate_step_input": { "total": 279.22271951644086, "count": 693848, "is_parallel": true, "self": 279.22271951644086 }, "communicator.exchange": { "total": 5114.488229378101, "count": 693848, "is_parallel": true, "self": 5114.488229378101 }, "steps_from_proto": { "total": 1142.767512208803, "count": 1387696, "is_parallel": true, "self": 249.0457277819213, "children": { "_process_rank_one_or_two_observation": { "total": 893.7217844268818, "count": 5550784, "is_parallel": true, "self": 893.7217844268818 } } } } } } } } } } }, "trainer_advance": { "total": 25039.473945075784, "count": 693848, "self": 130.10383324747454, "children": { "process_trajectory": { "total": 3508.380278649318, "count": 693848, "self": 3504.2055523923173, "children": { "RLTrainer._checkpoint": { "total": 4.174726257000657, "count": 20, "self": 4.174726257000657 } } }, "_update_policy": { "total": 21400.989833178992, "count": 485, "self": 1514.5387351270983, "children": { "TorchPOCAOptimizer.update": { "total": 19886.451098051893, "count": 14550, "self": 19886.451098051893 } } } } } } }, "trainer_threads": { "total": 1.0080038919113576e-06, "count": 1, "self": 1.0080038919113576e-06 }, "TrainerController._save_models": { "total": 0.20231456499459455, "count": 1, "self": 0.001523282000562176, "children": { "RLTrainer._checkpoint": { "total": 0.20079128299403237, "count": 1, "self": 0.20079128299403237 } } } } } } }