{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.263975143432617, "min": 3.263975143432617, "max": 3.2955996990203857, "count": 9 }, "SoccerTwos.Policy.Entropy.sum": { "value": 67264.0, "min": 6402.54248046875, "max": 105459.1875, "count": 9 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 668.625, "max": 999.0, "count": 9 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 7992.0, "max": 29000.0, "count": 9 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.0613811220826, "min": 1196.80641892118, "max": 1197.765044887543, "count": 7 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7182.368286732496, "min": 2393.61283784236, "max": 9582.120359100343, "count": 7 }, "SoccerTwos.Step.mean": { "value": 89482.0, "min": 9744.0, "max": 89482.0, "count": 9 }, "SoccerTwos.Step.sum": { "value": 89482.0, "min": 9744.0, "max": 89482.0, "count": 9 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.05293229967355728, "min": 0.05293229967355728, "max": 0.10084670037031174, "count": 9 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.5293229818344116, "min": 0.5293229818344116, "max": 1.3110071420669556, "count": 9 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05223597213625908, "min": 0.05223597213625908, "max": 0.10084545612335205, "count": 9 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5223597288131714, "min": 0.5223597288131714, "max": 1.3109909296035767, "count": 9 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 9 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 9 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.20542500168085098, "count": 9 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 3.2868000268936157, "count": 9 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.20542500168085098, "count": 9 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 3.2868000268936157, "count": 9 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 9 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013374029862461612, "min": 0.013374029862461612, "max": 0.015870314958588913, "count": 3 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013374029862461612, "min": 0.013374029862461612, "max": 0.015870314958588913, "count": 3 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0027596512072098752, "min": 0.00017736044222450194, "max": 0.004252468582051687, "count": 3 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0027596512072098752, "min": 0.00017736044222450194, "max": 0.004252468582051687, "count": 3 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0027632934739813208, "min": 0.00020425480130749444, "max": 0.0036879267173413285, "count": 3 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0027632934739813208, "min": 0.00020425480130749444, "max": 0.0036879267173413285, "count": 3 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 3 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 3 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 3 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 3 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 3 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716433904", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/bornier/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716434065" }, "total": 161.63042150800084, "count": 1, "self": 0.12480437600061123, "children": { "run_training.setup": { "total": 0.01991928799998277, "count": 1, "self": 0.01991928799998277 }, "TrainerController.start_learning": { "total": 161.48569784400024, "count": 1, "self": 0.09698929497426434, "children": { "TrainerController._reset_env": { "total": 0.844703235000452, "count": 1, "self": 0.844703235000452 }, "TrainerController.advance": { "total": 160.4508481930252, "count": 6301, "self": 0.09301975104699522, "children": { "env_step": { "total": 84.65789122996102, "count": 6301, "self": 67.38305985401439, "children": { "SubprocessEnvManager._take_step": { "total": 17.21408461997453, "count": 6301, "self": 0.5949912809082889, "children": { "TorchPolicy.evaluate": { "total": 16.61909333906624, "count": 12540, "self": 16.61909333906624 } } }, "workers": { "total": 0.06074675597210444, "count": 6300, "self": 0.0, "children": { "worker_root": { "total": 161.26679795799555, "count": 6300, "is_parallel": true, "self": 105.09722414995849, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001421345999915502, "count": 2, "is_parallel": true, "self": 0.0003609350005717715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010604109993437305, "count": 8, "is_parallel": true, "self": 0.0010604109993437305 } } }, "UnityEnvironment.step": { "total": 0.01756858899989311, "count": 1, "is_parallel": true, "self": 0.0004484769988266635, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000433956000051694, "count": 1, "is_parallel": true, "self": 0.000433956000051694 }, "communicator.exchange": { "total": 0.01561685800061241, "count": 1, "is_parallel": true, "self": 0.01561685800061241 }, "steps_from_proto": { "total": 0.0010692980004023411, "count": 2, "is_parallel": true, "self": 0.0002262539992443635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008430440011579776, "count": 8, "is_parallel": true, "self": 0.0008430440011579776 } } } } } } }, "UnityEnvironment.step": { "total": 56.16957380803706, "count": 6299, "is_parallel": true, "self": 3.1877515409378248, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4795013150223895, "count": 6299, "is_parallel": true, "self": 2.4795013150223895 }, "communicator.exchange": { "total": 41.24824364100459, "count": 6299, "is_parallel": true, "self": 41.24824364100459 }, "steps_from_proto": { "total": 9.254077311072251, "count": 12598, "is_parallel": true, "self": 1.6652363000875994, "children": { "_process_rank_one_or_two_observation": { "total": 7.588841010984652, "count": 50392, "is_parallel": true, "self": 7.588841010984652 } } } } } } } } } } }, "trainer_advance": { "total": 75.69993721201718, "count": 6300, "self": 0.9287074210224091, "children": { "process_trajectory": { "total": 10.216067085994837, "count": 6300, "self": 10.216067085994837 }, "_update_policy": { "total": 64.55516270499993, "count": 4, "self": 7.294472123001469, "children": { "TorchPOCAOptimizer.update": { "total": 57.26069058199846, "count": 129, "self": 57.26069058199846 } } } } } } }, "trainer_threads": { "total": 8.489996616845019e-07, "count": 1, "self": 8.489996616845019e-07 }, "TrainerController._save_models": { "total": 0.09315627200066956, "count": 1, "self": 0.001375828001073387, "children": { "RLTrainer._checkpoint": { "total": 0.09178044399959617, "count": 1, "self": 0.09178044399959617 } } } } } } }