{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6478638648986816, "min": 2.64497971534729, "max": 2.910040855407715, "count": 99 }, "SoccerTwos.Policy.Entropy.sum": { "value": 56939.6640625, "min": 39565.4296875, "max": 75923.484375, "count": 99 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.56756756756756, "min": 58.23809523809524, "max": 241.95, "count": 99 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19112.0, "min": 13404.0, "max": 22252.0, "count": 99 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1412.0522756934085, "min": 1323.6065140054525, "max": 1425.1974969013027, "count": 99 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208983.73680262448, "min": 53079.97955308974, "max": 238000.19807624962, "count": 99 }, "SoccerTwos.Step.mean": { "value": 5749994.0, "min": 4769938.0, "max": 5749994.0, "count": 99 }, "SoccerTwos.Step.sum": { "value": 5749994.0, "min": 4769938.0, "max": 5749994.0, "count": 99 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.028790147975087166, "min": -0.04101934656500816, "max": 0.09027662128210068, "count": 99 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.260941982269287, "min": -5.045379638671875, "max": 11.24030876159668, "count": 99 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.032357506453990936, "min": -0.03689615800976753, "max": 0.08805786818265915, "count": 99 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.788910865783691, "min": -4.538227558135986, "max": 10.536680221557617, "count": 99 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 99 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 99 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09212432117075534, "min": -0.3625368428857703, "max": 0.39829629714842196, "count": 99 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.63439953327179, "min": -33.321199893951416, "max": 43.01600009202957, "count": 99 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09212432117075534, "min": -0.3625368428857703, "max": 0.39829629714842196, "count": 99 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.63439953327179, "min": -33.321199893951416, "max": 43.01600009202957, "count": 99 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 99 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 99 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015930675513421495, "min": 0.011518537097920974, "max": 0.02257696205178945, "count": 47 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015930675513421495, "min": 0.011518537097920974, "max": 0.02257696205178945, "count": 47 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06051712979873022, "min": 0.03329648443808158, "max": 0.06932095438241959, "count": 47 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06051712979873022, "min": 0.03329648443808158, "max": 0.06932095438241959, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0617528443535169, "min": 0.03377765975892544, "max": 0.07101012269655864, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0617528443535169, "min": 0.03377765975892544, "max": 0.07101012269655864, "count": 47 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 47 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 47 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 47 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 47 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690883855", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu", "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": "1690887963" }, "total": 4107.853062852, "count": 1, "self": 0.5270315910001955, "children": { "run_training.setup": { "total": 0.04542847300035646, "count": 1, "self": 0.04542847300035646 }, "TrainerController.start_learning": { "total": 4107.280602788, "count": 1, "self": 2.857072912118383, "children": { "TrainerController._reset_env": { "total": 1.4553741960007756, "count": 6, "self": 1.4553741960007756 }, "TrainerController.advance": { "total": 4102.65817443788, "count": 66248, "self": 2.8340780267208174, "children": { "env_step": { "total": 2304.179882034283, "count": 66248, "self": 1944.8308511348696, "children": { "SubprocessEnvManager._take_step": { "total": 357.67793084941513, "count": 66248, "self": 18.838583014250617, "children": { "TorchPolicy.evaluate": { "total": 338.8393478351645, "count": 124596, "self": 338.8393478351645 } } }, "workers": { "total": 1.671100049998131, "count": 66248, "self": 0.0, "children": { "worker_root": { "total": 4084.930824363075, "count": 66248, "is_parallel": true, "self": 2466.000282550036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033345209994877223, "count": 2, "is_parallel": true, "self": 0.0008165080016624415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025180129978252808, "count": 8, "is_parallel": true, "self": 0.0025180129978252808 } } }, "UnityEnvironment.step": { "total": 0.0472815150005772, "count": 1, "is_parallel": true, "self": 0.0014041190006537363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009399139999004547, "count": 1, "is_parallel": true, "self": 0.0009399139999004547 }, "communicator.exchange": { "total": 0.04066125200006354, "count": 1, "is_parallel": true, "self": 0.04066125200006354 }, "steps_from_proto": { "total": 0.004276229999959469, "count": 2, "is_parallel": true, "self": 0.000782805000199005, "children": { "_process_rank_one_or_two_observation": { "total": 0.003493424999760464, "count": 8, "is_parallel": true, "self": 0.003493424999760464 } } } } } } }, "steps_from_proto": { "total": 0.016577086002143915, "count": 10, "is_parallel": true, "self": 0.0030401580024772556, "children": { "_process_rank_one_or_two_observation": { "total": 0.01353692799966666, "count": 40, "is_parallel": true, "self": 0.01353692799966666 } } }, "UnityEnvironment.step": { "total": 1618.9139647270367, "count": 66247, "is_parallel": true, "self": 94.74951284725284, "children": { "UnityEnvironment._generate_step_input": { "total": 49.7337207289238, "count": 66247, "is_parallel": true, "self": 49.7337207289238 }, "communicator.exchange": { "total": 1173.826287938149, "count": 66247, "is_parallel": true, "self": 1173.826287938149 }, "steps_from_proto": { "total": 300.604443212711, "count": 132494, "is_parallel": true, "self": 54.332957335935134, "children": { "_process_rank_one_or_two_observation": { "total": 246.27148587677584, "count": 529976, "is_parallel": true, "self": 246.27148587677584 } } } } } } } } } } }, "trainer_advance": { "total": 1795.6442143768763, "count": 66248, "self": 20.65638680877055, "children": { "process_trajectory": { "total": 319.03219946210083, "count": 66248, "self": 318.58547976910086, "children": { "RLTrainer._checkpoint": { "total": 0.44671969299997727, "count": 2, "self": 0.44671969299997727 } } }, "_update_policy": { "total": 1455.955628106005, "count": 47, "self": 263.7310127390356, "children": { "TorchPOCAOptimizer.update": { "total": 1192.2246153669694, "count": 1410, "self": 1192.2246153669694 } } } } } } }, "trainer_threads": { "total": 1.7330003174720332e-06, "count": 1, "self": 1.7330003174720332e-06 }, "TrainerController._save_models": { "total": 0.3099795090001862, "count": 1, "self": 0.0022393920007743873, "children": { "RLTrainer._checkpoint": { "total": 0.30774011699941184, "count": 1, "self": 0.30774011699941184 } } } } } } }