{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.381679058074951, "min": 2.381679058074951, "max": 3.2957217693328857, "count": 318 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47100.0859375, "min": 21282.8359375, "max": 111307.671875, "count": 318 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.6, "min": 45.388888888888886, "max": 999.0, "count": 318 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19572.0, "min": 16480.0, "max": 23896.0, "count": 318 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1396.5866878541844, "min": 1164.638227331954, "max": 1396.5866878541844, "count": 306 }, "SoccerTwos.Self-play.ELO.sum": { "value": 293283.2044493787, "min": 2346.624302055422, "max": 301232.1724136205, "count": 306 }, "SoccerTwos.Step.mean": { "value": 3179830.0, "min": 9796.0, "max": 3179830.0, "count": 318 }, "SoccerTwos.Step.sum": { "value": 3179830.0, "min": 9796.0, "max": 3179830.0, "count": 318 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07734601944684982, "min": -0.10053784400224686, "max": 0.16369430720806122, "count": 318 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 16.242664337158203, "min": -13.10733413696289, "max": 26.38780975341797, "count": 318 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08359357714653015, "min": -0.10465110838413239, "max": 0.15987545251846313, "count": 318 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 17.554651260375977, "min": -13.670734405517578, "max": 27.632722854614258, "count": 318 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 318 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 318 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07631428525561378, "min": -0.5882352941176471, "max": 0.43317333857218426, "count": 318 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 16.025999903678894, "min": -38.56879997253418, "max": 63.01519989967346, "count": 318 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07631428525561378, "min": -0.5882352941176471, "max": 0.43317333857218426, "count": 318 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 16.025999903678894, "min": -38.56879997253418, "max": 63.01519989967346, "count": 318 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 318 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 318 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014854168063417697, "min": 0.010596308086921151, "max": 0.024019896207998197, "count": 151 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014854168063417697, "min": 0.010596308086921151, "max": 0.024019896207998197, "count": 151 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09196225752433142, "min": 0.00014300238678212432, "max": 0.0958377443253994, "count": 151 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09196225752433142, "min": 0.00014300238678212432, "max": 0.0958377443253994, "count": 151 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09401522179444631, "min": 0.00014358906082634348, "max": 0.09762040053804716, "count": 151 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09401522179444631, "min": 0.00014358906082634348, "max": 0.09762040053804716, "count": 151 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 151 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 151 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 151 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 151 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 151 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 151 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708610937", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\hyt\\.conda\\envs\\myenv\\Scripts\\mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1708624334" }, "total": 13396.970899499953, "count": 1, "self": 0.19421019963920116, "children": { "run_training.setup": { "total": 0.11652000015601516, "count": 1, "self": 0.11652000015601516 }, "TrainerController.start_learning": { "total": 13396.660169300158, "count": 1, "self": 7.076584449503571, "children": { "TrainerController._reset_env": { "total": 5.286594799719751, "count": 16, "self": 5.286594799719751 }, "TrainerController.advance": { "total": 13384.056613751221, "count": 210436, "self": 7.244138726498932, "children": { "env_step": { "total": 5990.032013793942, "count": 210436, "self": 4738.054129078519, "children": { "SubprocessEnvManager._take_step": { "total": 1247.2681002654135, "count": 210436, "self": 39.99311551917344, "children": { "TorchPolicy.evaluate": { "total": 1207.27498474624, "count": 405466, "self": 1207.27498474624 } } }, "workers": { "total": 4.709784450009465, "count": 210436, "self": 0.0, "children": { "worker_root": { "total": 13383.674269352108, "count": 210436, "is_parallel": true, "self": 9560.35083931638, "children": { "steps_from_proto": { "total": 0.04339379956945777, "count": 32, "is_parallel": true, "self": 0.008767997846007347, "children": { "_process_rank_one_or_two_observation": { "total": 0.03462580172345042, "count": 128, "is_parallel": true, "self": 0.03462580172345042 } } }, "UnityEnvironment.step": { "total": 3823.2800362361595, "count": 210436, "is_parallel": true, "self": 207.09354672720656, "children": { "UnityEnvironment._generate_step_input": { "total": 154.42086639534682, "count": 210436, "is_parallel": true, "self": 154.42086639534682 }, "communicator.exchange": { "total": 2794.48251492111, "count": 210436, "is_parallel": true, "self": 2794.48251492111 }, "steps_from_proto": { "total": 667.283108192496, "count": 420872, "is_parallel": true, "self": 128.65287365205586, "children": { "_process_rank_one_or_two_observation": { "total": 538.6302345404401, "count": 1683488, "is_parallel": true, "self": 538.6302345404401 } } } } } } } } } } }, "trainer_advance": { "total": 7386.780461230781, "count": 210435, "self": 45.42298658331856, "children": { "process_trajectory": { "total": 957.8295357497409, "count": 210435, "self": 956.4663030495867, "children": { "RLTrainer._checkpoint": { "total": 1.3632327001541853, "count": 6, "self": 1.3632327001541853 } } }, "_update_policy": { "total": 6383.5279388977215, "count": 151, "self": 521.3205864042975, "children": { "TorchPOCAOptimizer.update": { "total": 5862.207352493424, "count": 4530, "self": 5862.207352493424 } } } } } } }, "trainer_threads": { "total": 2.00001522898674e-06, "count": 1, "self": 2.00001522898674e-06 }, "TrainerController._save_models": { "total": 0.24037429969757795, "count": 1, "self": 0.014842699281871319, "children": { "RLTrainer._checkpoint": { "total": 0.22553160041570663, "count": 1, "self": 0.22553160041570663 } } } } } } }