{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4363939762115479, "min": 1.3503320217132568, "max": 3.2957546710968018, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28681.916015625, "min": 23196.216796875, "max": 124502.9140625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.98684210526316, "min": 38.22047244094488, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19756.0, "min": 15244.0, "max": 26476.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1648.8015793099883, "min": 1196.0437918589532, "max": 1686.2468181253266, "count": 4999 }, "SoccerTwos.Self-play.ELO.sum": { "value": 250617.8400551182, "min": 2394.311373924607, "max": 389700.5828417282, "count": 4999 }, "SoccerTwos.Step.mean": { "value": 49999976.0, "min": 9254.0, "max": 49999976.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999976.0, "min": 9254.0, "max": 49999976.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01695444993674755, "min": -0.132838636636734, "max": 0.16042351722717285, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.560122013092041, "min": -24.30330467224121, "max": 31.2825870513916, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.019264034926891327, "min": -0.13162541389465332, "max": 0.15800507366657257, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.9088692665100098, "min": -24.16169548034668, "max": 30.810989379882812, "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": -0.015650334342426023, "min": -0.5294117647058824, "max": 0.46835555964046055, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.3632004857063293, "min": -66.39160001277924, "max": 52.063599705696106, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.015650334342426023, "min": -0.5294117647058824, "max": 0.46835555964046055, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.3632004857063293, "min": -66.39160001277924, "max": 52.063599705696106, "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": 0.020285495067946614, "min": 0.009509219172468875, "max": 0.02645891107774029, "count": 2426 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020285495067946614, "min": 0.009509219172468875, "max": 0.02645891107774029, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10916803305347761, "min": 0.0011797005446472517, "max": 0.12795470307270687, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10916803305347761, "min": 0.0011797005446472517, "max": 0.12795470307270687, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11020258565743764, "min": 0.001188150733166064, "max": 0.13052797242999076, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11020258565743764, "min": 0.001188150733166064, "max": 0.13052797242999076, "count": 2426 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676241851", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/konrad/miniconda3/envs/rl_ai_vs_ai/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1676307613" }, "total": 65761.664129426, "count": 1, "self": 0.2691828070237534, "children": { "run_training.setup": { "total": 0.00772888699430041, "count": 1, "self": 0.00772888699430041 }, "TrainerController.start_learning": { "total": 65761.38721773199, "count": 1, "self": 68.87260482228885, "children": { "TrainerController._reset_env": { "total": 6.108942669961834, "count": 250, "self": 6.108942669961834 }, "TrainerController.advance": { "total": 65686.22484355074, "count": 3457920, "self": 65.07742408150807, "children": { "env_step": { "total": 46744.5257107698, "count": 3457920, "self": 34186.372190445996, "children": { "SubprocessEnvManager._take_step": { "total": 12520.238155457206, "count": 3457920, "self": 333.48648220101313, "children": { "TorchPolicy.evaluate": { "total": 12186.751673256193, "count": 6277096, "self": 12186.751673256193 } } }, "workers": { "total": 37.915364866596065, "count": 3457920, "self": 0.0, "children": { "worker_root": { "total": 65677.59810379175, "count": 3457920, "is_parallel": true, "self": 38147.21769326538, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019695220107678324, "count": 2, "is_parallel": true, "self": 0.0005542150029214099, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014153070078464225, "count": 8, "is_parallel": true, "self": 0.0014153070078464225 } } }, "UnityEnvironment.step": { "total": 0.020286636005039327, "count": 1, "is_parallel": true, "self": 0.0005079609982203692, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003870410000672564, "count": 1, "is_parallel": true, "self": 0.0003870410000672564 }, "communicator.exchange": { "total": 0.017914305004524067, "count": 1, "is_parallel": true, "self": 0.017914305004524067 }, "steps_from_proto": { "total": 0.0014773290022276342, "count": 2, "is_parallel": true, "self": 0.0003302739787613973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011470550234662369, "count": 8, "is_parallel": true, "self": 0.0011470550234662369 } } } } } } }, "UnityEnvironment.step": { "total": 27529.993976432233, "count": 3457919, "is_parallel": true, "self": 1644.5499559181917, "children": { "UnityEnvironment._generate_step_input": { "total": 1065.2899068473198, "count": 3457919, "is_parallel": true, "self": 1065.2899068473198 }, "communicator.exchange": { "total": 20114.62883969328, "count": 3457919, "is_parallel": true, "self": 20114.62883969328 }, "steps_from_proto": { "total": 4705.525273973442, "count": 6915838, "is_parallel": true, "self": 1022.7446160347754, "children": { "_process_rank_one_or_two_observation": { "total": 3682.780657938667, "count": 27663352, "is_parallel": true, "self": 3682.780657938667 } } } } }, "steps_from_proto": { "total": 0.386434094136348, "count": 498, "is_parallel": true, "self": 0.08291502288193442, "children": { "_process_rank_one_or_two_observation": { "total": 0.3035190712544136, "count": 1992, "is_parallel": true, "self": 0.3035190712544136 } } } } } } } } }, "trainer_advance": { "total": 18876.62170869943, "count": 3457920, "self": 409.5243336641288, "children": { "process_trajectory": { "total": 7357.342531291666, "count": 3457920, "self": 7338.3734092125815, "children": { "RLTrainer._checkpoint": { "total": 18.969122079084627, "count": 100, "self": 18.969122079084627 } } }, "_update_policy": { "total": 11109.754843743634, "count": 2426, "self": 6401.967426916919, "children": { "TorchPOCAOptimizer.update": { "total": 4707.787416826715, "count": 72780, "self": 4707.787416826715 } } } } } } }, "trainer_threads": { "total": 8.360075298696756e-07, "count": 1, "self": 8.360075298696756e-07 }, "TrainerController._save_models": { "total": 0.1808258529927116, "count": 1, "self": 0.0011467889999039471, "children": { "RLTrainer._checkpoint": { "total": 0.17967906399280764, "count": 1, "self": 0.17967906399280764 } } } } } } }