{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5180662870407104, "min": 1.4537625312805176, "max": 3.295696258544922, "count": 1751 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29001.138671875, "min": 19740.61328125, "max": 105462.28125, "count": 1751 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.51162790697674, "min": 38.330708661417326, "max": 999.0, "count": 1751 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19784.0, "min": 8732.0, "max": 27588.0, "count": 1751 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1514.9747793086233, "min": 1188.4667000396976, "max": 1575.5373644724887, "count": 1748 }, "SoccerTwos.Self-play.ELO.sum": { "value": 260575.6620410832, "min": 2388.11500602936, "max": 383159.1370412271, "count": 1748 }, "SoccerTwos.Step.mean": { "value": 17509985.0, "min": 9450.0, "max": 17509985.0, "count": 1751 }, "SoccerTwos.Step.sum": { "value": 17509985.0, "min": 9450.0, "max": 17509985.0, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.020330609753727913, "min": -0.14643694460391998, "max": 0.17252300679683685, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.4968650341033936, "min": -25.919340133666992, "max": 24.193138122558594, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.019250068813562393, "min": -0.14864228665828705, "max": 0.17098000645637512, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.311011791229248, "min": -26.30968475341797, "max": 24.28445816040039, "count": 1751 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1751 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.16332209283529325, "min": -0.6671789461060574, "max": 0.5629405435678121, "count": 1751 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 28.09139996767044, "min": -60.07320040464401, "max": 52.2077996134758, "count": 1751 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.16332209283529325, "min": -0.6671789461060574, "max": 0.5629405435678121, "count": 1751 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 28.09139996767044, "min": -60.07320040464401, "max": 52.2077996134758, "count": 1751 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1751 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1751 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017533206019046097, "min": 0.009657192969461903, "max": 0.025968049650934213, "count": 847 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017533206019046097, "min": 0.009657192969461903, "max": 0.025968049650934213, "count": 847 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09411052390933036, "min": 0.00092769174661953, "max": 0.12981676012277604, "count": 847 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09411052390933036, "min": 0.00092769174661953, "max": 0.12981676012277604, "count": 847 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09523837566375733, "min": 0.0009241009009807992, "max": 0.13323278203606606, "count": 847 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09523837566375733, "min": 0.0009241009009807992, "max": 0.13323278203606606, "count": 847 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 847 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 847 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 847 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 847 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 847 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 847 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685610016", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ai/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1685626797" }, "total": 16781.088473484007, "count": 1, "self": 0.0027533890097402036, "children": { "run_training.setup": { "total": 0.005900299991481006, "count": 1, "self": 0.005900299991481006 }, "TrainerController.start_learning": { "total": 16781.079819795006, "count": 1, "self": 16.76027166834683, "children": { "TrainerController._reset_env": { "total": 6.7389328529679915, "count": 88, "self": 6.7389328529679915 }, "TrainerController.advance": { "total": 16757.257331969697, "count": 1216495, "self": 16.612954382479074, "children": { "env_step": { "total": 12173.069506224012, "count": 1216495, "self": 8998.111707923963, "children": { "SubprocessEnvManager._take_step": { "total": 3165.3512335359264, "count": 1216495, "self": 91.6559871135396, "children": { "TorchPolicy.evaluate": { "total": 3073.695246422387, "count": 2201686, "self": 3073.695246422387 } } }, "workers": { "total": 9.606564764122595, "count": 1216494, "self": 0.0, "children": { "worker_root": { "total": 16759.442294077628, "count": 1216494, "is_parallel": true, "self": 9441.820313411052, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012385250010993332, "count": 2, "is_parallel": true, "self": 0.0003075519925914705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009309730085078627, "count": 8, "is_parallel": true, "self": 0.0009309730085078627 } } }, "UnityEnvironment.step": { "total": 0.013737829998717643, "count": 1, "is_parallel": true, "self": 0.0003534809948178008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002459980023559183, "count": 1, "is_parallel": true, "self": 0.0002459980023559183 }, "communicator.exchange": { "total": 0.01212592699448578, "count": 1, "is_parallel": true, "self": 0.01212592699448578 }, "steps_from_proto": { "total": 0.0010124240070581436, "count": 2, "is_parallel": true, "self": 0.00021697398915421218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007954500179039314, "count": 8, "is_parallel": true, "self": 0.0007954500179039314 } } } } } } }, "UnityEnvironment.step": { "total": 7317.5358168534, "count": 1216493, "is_parallel": true, "self": 423.9135033531056, "children": { "UnityEnvironment._generate_step_input": { "total": 272.44869865241344, "count": 1216493, "is_parallel": true, "self": 272.44869865241344 }, "communicator.exchange": { "total": 5442.560499921397, "count": 1216493, "is_parallel": true, "self": 5442.560499921397 }, "steps_from_proto": { "total": 1178.6131149264838, "count": 2432986, "is_parallel": true, "self": 246.49301429046318, "children": { "_process_rank_one_or_two_observation": { "total": 932.1201006360207, "count": 9731944, "is_parallel": true, "self": 932.1201006360207 } } } } }, "steps_from_proto": { "total": 0.08616381317551713, "count": 174, "is_parallel": true, "self": 0.01794812228763476, "children": { "_process_rank_one_or_two_observation": { "total": 0.06821569088788237, "count": 696, "is_parallel": true, "self": 0.06821569088788237 } } } } } } } } }, "trainer_advance": { "total": 4567.574871363206, "count": 1216494, "self": 99.60447046456102, "children": { "process_trajectory": { "total": 1860.6178297195584, "count": 1216494, "self": 1852.5881380495994, "children": { "RLTrainer._checkpoint": { "total": 8.029691669958993, "count": 35, "self": 8.029691669958993 } } }, "_update_policy": { "total": 2607.352571179086, "count": 848, "self": 1496.101430622337, "children": { "TorchPOCAOptimizer.update": { "total": 1111.2511405567493, "count": 25446, "self": 1111.2511405567493 } } } } } } }, "trainer_threads": { "total": 8.549977792426944e-07, "count": 1, "self": 8.549977792426944e-07 }, "TrainerController._save_models": { "total": 0.32328244899690617, "count": 1, "self": 0.0010382890031905845, "children": { "RLTrainer._checkpoint": { "total": 0.3222441599937156, "count": 1, "self": 0.3222441599937156 } } } } } } }