{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2576279640197754, "min": 3.2537851333618164, "max": 3.295717716217041, "count": 13 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57542.73828125, "min": 33861.296875, "max": 105462.96875, "count": 13 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 751.8333333333334, "min": 185.5, "max": 999.0, "count": 13 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18044.0, "min": 1484.0, "max": 31436.0, "count": 13 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.9242137158324, "min": 1199.3173316810933, "max": 1204.9242137158324, "count": 12 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7229.545282294995, "min": 2403.9479401854865, "max": 9617.75730912673, "count": 12 }, "SoccerTwos.Step.mean": { "value": 129982.0, "min": 9738.0, "max": 129982.0, "count": 13 }, "SoccerTwos.Step.sum": { "value": 129982.0, "min": 9738.0, "max": 129982.0, "count": 13 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.014644455164670944, "min": 0.014644455164670944, "max": 0.032572291791439056, "count": 13 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.19037792086601257, "min": 0.1794193983078003, "max": 0.45596224069595337, "count": 13 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.017978785559535027, "min": 0.01674814336001873, "max": 0.032895006239414215, "count": 13 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.2337242215871811, "min": 0.19487503170967102, "max": 0.4557684063911438, "count": 13 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.38461538461538464, "min": -0.38461538461538464, "max": 0.19830769300460815, "count": 13 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.0, "min": -5.0, "max": 2.578000009059906, "count": 13 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.38461538461538464, "min": -0.38461538461538464, "max": 0.19830769300460815, "count": 13 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.0, "min": -5.0, "max": 2.578000009059906, "count": 13 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0156993512381329, "min": 0.01255239952976505, "max": 0.019423652351057776, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0156993512381329, "min": 0.01255239952976505, "max": 0.019423652351057776, "count": 5 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0007048266459605656, "min": 0.0007048266459605656, "max": 0.0028398649961066742, "count": 5 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0007048266459605656, "min": 0.0007048266459605656, "max": 0.0028398649961066742, "count": 5 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007757227945451935, "min": 0.0007757227945451935, "max": 0.0029023472762977082, "count": 5 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007757227945451935, "min": 0.0007757227945451935, "max": 0.0029023472762977082, "count": 5 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 5 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 5 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 5 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 5 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 5 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677009058", "python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env /content/SoccerTwos/SoccerTwos.x86_64 --run-id=resnet --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1677012378" }, "total": 3320.1723494049997, "count": 1, "self": 0.1126849209995271, "children": { "run_training.setup": { "total": 0.023702585000023646, "count": 1, "self": 0.023702585000023646 }, "TrainerController.start_learning": { "total": 3320.035961899, "count": 1, "self": 0.4331714710019696, "children": { "TrainerController._reset_env": { "total": 2.1375977899999725, "count": 1, "self": 2.1375977899999725 }, "TrainerController.advance": { "total": 3316.528596789998, "count": 9113, "self": 0.5762363189587631, "children": { "env_step": { "total": 2684.406460440016, "count": 9113, "self": 2614.6015797100313, "children": { "SubprocessEnvManager._take_step": { "total": 69.52509770499569, "count": 9113, "self": 3.0549601939927697, "children": { "TorchPolicy.evaluate": { "total": 66.47013751100292, "count": 18130, "self": 66.47013751100292 } } }, "workers": { "total": 0.2797830249888875, "count": 9112, "self": 0.0, "children": { "worker_root": { "total": 3313.468283388007, "count": 9112, "is_parallel": true, "self": 760.2316764310358, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.018969138999977986, "count": 2, "is_parallel": true, "self": 0.012128357999813488, "children": { "_process_rank_one_or_two_observation": { "total": 0.0068407810001644975, "count": 8, "is_parallel": true, "self": 0.0068407810001644975 } } }, "UnityEnvironment.step": { "total": 0.6232171149999886, "count": 1, "is_parallel": true, "self": 0.002970763000007537, "children": { "UnityEnvironment._generate_step_input": { "total": 0.004098444999954154, "count": 1, "is_parallel": true, "self": 0.004098444999954154 }, "communicator.exchange": { "total": 0.5888043070000322, "count": 1, "is_parallel": true, "self": 0.5888043070000322 }, "steps_from_proto": { "total": 0.027343599999994694, "count": 2, "is_parallel": true, "self": 0.012229096999931244, "children": { "_process_rank_one_or_two_observation": { "total": 0.01511450300006345, "count": 8, "is_parallel": true, "self": 0.01511450300006345 } } } } } } }, "UnityEnvironment.step": { "total": 2553.236606956971, "count": 9111, "is_parallel": true, "self": 10.095866892022059, "children": { "UnityEnvironment._generate_step_input": { "total": 50.37109838598758, "count": 9111, "is_parallel": true, "self": 50.37109838598758 }, "communicator.exchange": { "total": 2398.99589506199, "count": 9111, "is_parallel": true, "self": 2398.99589506199 }, "steps_from_proto": { "total": 93.77374661697161, "count": 18222, "is_parallel": true, "self": 14.795739507032522, "children": { "_process_rank_one_or_two_observation": { "total": 78.97800710993909, "count": 72888, "is_parallel": true, "self": 78.97800710993909 } } } } } } } } } } }, "trainer_advance": { "total": 631.5459000310234, "count": 9112, "self": 3.6506919360103893, "children": { "process_trajectory": { "total": 74.31002424201347, "count": 9112, "self": 74.31002424201347 }, "_update_policy": { "total": 553.5851838529995, "count": 6, "self": 42.30831541499742, "children": { "TorchPOCAOptimizer.update": { "total": 511.2768684380021, "count": 192, "self": 511.2768684380021 } } } } } } }, "trainer_threads": { "total": 2.159999894502107e-06, "count": 1, "self": 2.159999894502107e-06 }, "TrainerController._save_models": { "total": 0.9365936880003574, "count": 1, "self": 0.005252573000234406, "children": { "RLTrainer._checkpoint": { "total": 0.931341115000123, "count": 1, "self": 0.931341115000123 } } } } } } }