{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5091946125030518, "min": 1.325435996055603, "max": 3.295685291290283, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31439.54296875, "min": 21926.326171875, "max": 110975.4609375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.8955223880597, "min": 37.26923076923077, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19000.0, "min": 7992.0, "max": 31188.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1801.7418215807775, "min": 1198.190099908711, "max": 1835.7299469282439, "count": 4958 }, "SoccerTwos.Self-play.ELO.sum": { "value": 241433.4040918242, "min": 2396.380199817422, "max": 432303.4689743812, "count": 4958 }, "SoccerTwos.Step.mean": { "value": 49999967.0, "min": 9502.0, "max": 49999967.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999967.0, "min": 9502.0, "max": 49999967.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.021310919895768166, "min": -0.1324259340763092, "max": 0.19452635943889618, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.876974105834961, "min": -22.916593551635742, "max": 26.819599151611328, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02532254531979561, "min": -0.1327137053012848, "max": 0.19241538643836975, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.418543577194214, "min": -22.944385528564453, "max": 26.660112380981445, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09117629616348832, "min": -0.5, "max": 0.4508639945834875, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -12.308799982070923, "min": -68.18639993667603, "max": 70.21480011940002, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09117629616348832, "min": -0.5, "max": 0.4508639945834875, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -12.308799982070923, "min": -68.18639993667603, "max": 70.21480011940002, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01989641071219618, "min": 0.010296740662306547, "max": 0.026408996262277166, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01989641071219618, "min": 0.010296740662306547, "max": 0.026408996262277166, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10399795373280843, "min": 5.052829351370747e-07, "max": 0.13746680021286012, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10399795373280843, "min": 5.052829351370747e-07, "max": 0.13746680021286012, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10489270761609078, "min": 3.9180880359405513e-07, "max": 0.13886504471302033, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10489270761609078, "min": 3.9180880359405513e-07, "max": 0.13886504471302033, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679394437", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/madd/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --force --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1679445552" }, "total": 51115.75790369604, "count": 1, "self": 0.27135065908078104, "children": { "run_training.setup": { "total": 0.006677009048871696, "count": 1, "self": 0.006677009048871696 }, "TrainerController.start_learning": { "total": 51115.47987602791, "count": 1, "self": 44.699953548726626, "children": { "TrainerController._reset_env": { "total": 5.279510647407733, "count": 250, "self": 5.279510647407733 }, "TrainerController.advance": { "total": 51065.3623340216, "count": 3454035, "self": 42.94749108084943, "children": { "env_step": { "total": 37613.22994301212, "count": 3454035, "self": 29650.399021285702, "children": { "SubprocessEnvManager._take_step": { "total": 7932.426932244911, "count": 3454035, "self": 265.4437365505146, "children": { "TorchPolicy.evaluate": { "total": 7666.983195694396, "count": 6279544, "self": 7666.983195694396 } } }, "workers": { "total": 30.40398948150687, "count": 3454035, "self": 0.0, "children": { "worker_root": { "total": 51055.4050460998, "count": 3454035, "is_parallel": true, "self": 26617.727656310075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014895820058882236, "count": 2, "is_parallel": true, "self": 0.00045397202484309673, "children": { "_process_rank_one_or_two_observation": { "total": 0.001035609981045127, "count": 8, "is_parallel": true, "self": 0.001035609981045127 } } }, "UnityEnvironment.step": { "total": 0.016421745996922255, "count": 1, "is_parallel": true, "self": 0.00036188610829412937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026072398759424686, "count": 1, "is_parallel": true, "self": 0.00026072398759424686 }, "communicator.exchange": { "total": 0.014791199006140232, "count": 1, "is_parallel": true, "self": 0.014791199006140232 }, "steps_from_proto": { "total": 0.0010079368948936462, "count": 2, "is_parallel": true, "self": 0.00021583097986876965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007921059150248766, "count": 8, "is_parallel": true, "self": 0.0007921059150248766 } } } } } } }, "UnityEnvironment.step": { "total": 24437.424309372902, "count": 3454034, "is_parallel": true, "self": 1201.1986244178843, "children": { "UnityEnvironment._generate_step_input": { "total": 807.0662587000988, "count": 3454034, "is_parallel": true, "self": 807.0662587000988 }, "communicator.exchange": { "total": 19068.473930052714, "count": 3454034, "is_parallel": true, "self": 19068.473930052714 }, "steps_from_proto": { "total": 3360.6854962022044, "count": 6908068, "is_parallel": true, "self": 682.2011010588612, "children": { "_process_rank_one_or_two_observation": { "total": 2678.484395143343, "count": 27632272, "is_parallel": true, "self": 2678.484395143343 } } } } }, "steps_from_proto": { "total": 0.25308041682001203, "count": 498, "is_parallel": true, "self": 0.0524178285850212, "children": { "_process_rank_one_or_two_observation": { "total": 0.20066258823499084, "count": 1992, "is_parallel": true, "self": 0.20066258823499084 } } } } } } } } }, "trainer_advance": { "total": 13409.18489992863, "count": 3454035, "self": 306.95177966193296, "children": { "process_trajectory": { "total": 4909.24327490665, "count": 3454035, "self": 4895.40603415505, "children": { "RLTrainer._checkpoint": { "total": 13.837240751599893, "count": 100, "self": 13.837240751599893 } } }, "_update_policy": { "total": 8192.989845360047, "count": 2424, "self": 5312.4901024515275, "children": { "TorchPOCAOptimizer.update": { "total": 2880.4997429085197, "count": 72729, "self": 2880.4997429085197 } } } } } } }, "trainer_threads": { "total": 6.891787052154541e-07, "count": 1, "self": 6.891787052154541e-07 }, "TrainerController._save_models": { "total": 0.13807712099514902, "count": 1, "self": 0.0012613199651241302, "children": { "RLTrainer._checkpoint": { "total": 0.1368158010300249, "count": 1, "self": 0.1368158010300249 } } } } } } }