{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.514999270439148, "min": 1.489595651626587, "max": 1.601452350616455, "count": 43 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31560.46484375, "min": 27883.697265625, "max": 34768.91796875, "count": 43 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.824175824175825, "min": 41.13559322033898, "max": 63.36363636363637, "count": 43 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19592.0, "min": 16812.0, "max": 20084.0, "count": 43 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1791.723449073225, "min": 1754.3428175876059, "max": 1791.723449073225, "count": 43 }, "SoccerTwos.Self-play.ELO.sum": { "value": 326093.66773132695, "min": 272477.7385629466, "max": 415596.7662303577, "count": 43 }, "SoccerTwos.Step.mean": { "value": 13279943.0, "min": 12859946.0, "max": 13279943.0, "count": 43 }, "SoccerTwos.Step.sum": { "value": 13279943.0, "min": 12859946.0, "max": 13279943.0, "count": 43 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06306133419275284, "min": -0.05972757562994957, "max": 0.07309861481189728, "count": 43 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 11.47716236114502, "min": -10.930146217346191, "max": 14.181131362915039, "count": 43 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06298738718032837, "min": -0.055884044617414474, "max": 0.0707717165350914, "count": 43 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 11.463704109191895, "min": -10.22677993774414, "max": 13.729713439941406, "count": 43 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 43 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 43 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.14293516337216555, "min": -0.2126644797663871, "max": 0.22874545199530466, "count": 43 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 26.01419973373413, "min": -38.91759979724884, "max": 42.61020004749298, "count": 43 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.14293516337216555, "min": -0.2126644797663871, "max": 0.22874545199530466, "count": 43 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 26.01419973373413, "min": -38.91759979724884, "max": 42.61020004749298, "count": 43 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01759544127077485, "min": 0.011227267006567369, "max": 0.020452462819715342, "count": 20 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01759544127077485, "min": 0.011227267006567369, "max": 0.020452462819715342, "count": 20 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11412317032615343, "min": 0.10178396105766296, "max": 0.12401819825172425, "count": 20 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11412317032615343, "min": 0.10178396105766296, "max": 0.12401819825172425, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11528436491886775, "min": 0.1030850184460481, "max": 0.1254842718442281, "count": 20 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11528436491886775, "min": 0.1030850184460481, "max": 0.1254842718442281, "count": 20 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 20 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 20 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 20 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 20 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 20 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713950149", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/robot/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos-24-test0.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-24-test0 --no-graphics --resume", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713950607" }, "total": 457.3718859350047, "count": 1, "self": 0.1159048219997203, "children": { "run_training.setup": { "total": 0.01975632600078825, "count": 1, "self": 0.01975632600078825 }, "TrainerController.start_learning": { "total": 457.2362247870042, "count": 1, "self": 0.4582937658269657, "children": { "TrainerController._reset_env": { "total": 1.0023442019955837, "count": 4, "self": 1.0023442019955837 }, "TrainerController.advance": { "total": 455.67333012618474, "count": 30291, "self": 0.4562869664368918, "children": { "env_step": { "total": 352.1429776112709, "count": 30291, "self": 262.03236804751214, "children": { "SubprocessEnvManager._take_step": { "total": 89.82456818577339, "count": 30291, "self": 2.607199358084472, "children": { "TorchPolicy.evaluate": { "total": 87.21736882768892, "count": 54098, "self": 87.21736882768892 } } }, "workers": { "total": 0.2860413779853843, "count": 30290, "self": 0.0, "children": { "worker_root": { "total": 456.40040704779676, "count": 30290, "is_parallel": true, "self": 242.38395667484292, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015634679948561825, "count": 2, "is_parallel": true, "self": 0.0003977819869760424, "children": { "_process_rank_one_or_two_observation": { "total": 0.00116568600788014, "count": 8, "is_parallel": true, "self": 0.00116568600788014 } } }, "UnityEnvironment.step": { "total": 0.017318722006166354, "count": 1, "is_parallel": true, "self": 0.0003682690003188327, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002611540039652027, "count": 1, "is_parallel": true, "self": 0.0002611540039652027 }, "communicator.exchange": { "total": 0.015684391000831965, "count": 1, "is_parallel": true, "self": 0.015684391000831965 }, "steps_from_proto": { "total": 0.001004908001050353, "count": 2, "is_parallel": true, "self": 0.00019816600979538634, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008067419912549667, "count": 8, "is_parallel": true, "self": 0.0008067419912549667 } } } } } } }, "steps_from_proto": { "total": 0.003151374992739875, "count": 6, "is_parallel": true, "self": 0.0005871999965165742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025641749962233007, "count": 24, "is_parallel": true, "self": 0.0025641749962233007 } } }, "UnityEnvironment.step": { "total": 214.0132989979611, "count": 30289, "is_parallel": true, "self": 11.56873725906189, "children": { "UnityEnvironment._generate_step_input": { "total": 6.9204708298057085, "count": 30289, "is_parallel": true, "self": 6.9204708298057085 }, "communicator.exchange": { "total": 164.13787390717334, "count": 30289, "is_parallel": true, "self": 164.13787390717334 }, "steps_from_proto": { "total": 31.38621700192016, "count": 60578, "is_parallel": true, "self": 5.944496136136877, "children": { "_process_rank_one_or_two_observation": { "total": 25.44172086578328, "count": 242312, "is_parallel": true, "self": 25.44172086578328 } } } } } } } } } } }, "trainer_advance": { "total": 103.07406554847694, "count": 30290, "self": 3.120524487036164, "children": { "process_trajectory": { "total": 52.969188115421275, "count": 30290, "self": 52.89213044641656, "children": { "RLTrainer._checkpoint": { "total": 0.07705766900471644, "count": 1, "self": 0.07705766900471644 } } }, "_update_policy": { "total": 46.9843529460195, "count": 20, "self": 29.815163639934326, "children": { "TorchPOCAOptimizer.update": { "total": 17.169189306085173, "count": 600, "self": 17.169189306085173 } } } } } } }, "trainer_threads": { "total": 7.839989848434925e-07, "count": 1, "self": 7.839989848434925e-07 }, "TrainerController._save_models": { "total": 0.10225590899790404, "count": 1, "self": 0.0007471069984603673, "children": { "RLTrainer._checkpoint": { "total": 0.10150880199944368, "count": 1, "self": 0.10150880199944368 } } } } } } }