{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.246417999267578, "min": 3.050156593322754, "max": 3.2879209518432617, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 103885.375, "min": 19072.3125, "max": 168756.203125, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 557.4, "min": 319.0, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22296.0, "min": 12788.0, "max": 26408.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1175.7556102442313, "min": 1146.4087410385055, "max": 1185.5659203576151, "count": 919 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11757.556102442313, "min": 2295.220358848017, "max": 23181.80128214334, "count": 919 }, "SoccerTwos.Step.mean": { "value": 14999320.0, "min": 5009061.0, "max": 14999320.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 14999320.0, "min": 5009061.0, "max": 14999320.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04412936046719551, "min": -0.24103452265262604, "max": 0.033582162111997604, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.882587194442749, "min": -5.6026411056518555, "max": 0.6278324723243713, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04412936046719551, "min": -0.24103452265262604, "max": 0.033582162111997604, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.882587194442749, "min": -5.6026411056518555, "max": 0.6278324723243713, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3083400011062622, "min": -0.7692307692307693, "max": 0.37272500433027744, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.166800022125244, "min": -12.69159996509552, "max": 7.467200011014938, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3083400011062622, "min": -0.7692307692307693, "max": 0.37272500433027744, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.166800022125244, "min": -12.69159996509552, "max": 7.467200011014938, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.12642634871881456, "min": 0.058891880031054215, "max": 0.18489151646693547, "count": 493 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.12642634871881456, "min": 0.058891880031054215, "max": 0.18489151646693547, "count": 493 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00633253084856733, "min": 7.239924562677895e-07, "max": 0.01663869137216049, "count": 493 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00633253084856733, "min": 7.239924562677895e-07, "max": 0.01663869137216049, "count": 493 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.00633253084856733, "min": 7.239924562677895e-07, "max": 0.01663869137216049, "count": 493 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.00633253084856733, "min": 7.239924562677895e-07, "max": 0.01663869137216049, "count": 493 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 493 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 493 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 493 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 493 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 493 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 493 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684130740", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/miki/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos-v3.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-v3 --no-graphics --resume", "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": "1.19.5", "end_time_seconds": "1684148854" }, "total": 18114.211095059, "count": 1, "self": 0.27357527798449155, "children": { "run_training.setup": { "total": 0.009219529005349614, "count": 1, "self": 0.009219529005349614 }, "TrainerController.start_learning": { "total": 18113.92830025201, "count": 1, "self": 14.40633160014113, "children": { "TrainerController._reset_env": { "total": 21.839517669883207, "count": 198, "self": 21.839517669883207 }, "TrainerController.advance": { "total": 18074.499120597975, "count": 710078, "self": 14.310009649780113, "children": { "env_step": { "total": 13632.4378354363, "count": 710078, "self": 8217.656848823332, "children": { "SubprocessEnvManager._take_step": { "total": 5406.534358140401, "count": 710078, "self": 97.22469455462124, "children": { "TorchPolicy.evaluate": { "total": 5309.30966358578, "count": 1409326, "self": 5309.30966358578 } } }, "workers": { "total": 8.246628472566954, "count": 710078, "self": 0.0, "children": { "worker_root": { "total": 18084.06854760695, "count": 710078, "is_parallel": true, "self": 11612.170828554634, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002709021995542571, "count": 2, "is_parallel": true, "self": 0.0005072740168543532, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022017479786882177, "count": 8, "is_parallel": true, "self": 0.0022017479786882177 } } }, "UnityEnvironment.step": { "total": 0.019676716008689255, "count": 1, "is_parallel": true, "self": 0.0004592890036292374, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036058700061403215, "count": 1, "is_parallel": true, "self": 0.00036058700061403215 }, "communicator.exchange": { "total": 0.01653556300152559, "count": 1, "is_parallel": true, "self": 0.01653556300152559 }, "steps_from_proto": { "total": 0.0023212770029203966, "count": 2, "is_parallel": true, "self": 0.00034243499976582825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019788420031545684, "count": 8, "is_parallel": true, "self": 0.0019788420031545684 } } } } } } }, "steps_from_proto": { "total": 0.45138581391074695, "count": 394, "is_parallel": true, "self": 0.06472570712503511, "children": { "_process_rank_one_or_two_observation": { "total": 0.38666010678571183, "count": 1576, "is_parallel": true, "self": 0.38666010678571183 } } }, "UnityEnvironment.step": { "total": 6471.446333238404, "count": 710077, "is_parallel": true, "self": 327.9030821932538, "children": { "UnityEnvironment._generate_step_input": { "total": 216.1317351411708, "count": 710077, "is_parallel": true, "self": 216.1317351411708 }, "communicator.exchange": { "total": 4298.20682969164, "count": 710077, "is_parallel": true, "self": 4298.20682969164 }, "steps_from_proto": { "total": 1629.2046862123389, "count": 1420154, "is_parallel": true, "self": 229.08357965866162, "children": { "_process_rank_one_or_two_observation": { "total": 1400.1211065536772, "count": 5680616, "is_parallel": true, "self": 1400.1211065536772 } } } } } } } } } } }, "trainer_advance": { "total": 4427.751275511895, "count": 710078, "self": 125.89967236529628, "children": { "process_trajectory": { "total": 1823.254267945551, "count": 710078, "self": 1765.1624900335155, "children": { "RLTrainer._checkpoint": { "total": 58.09177791203547, "count": 20, "self": 58.09177791203547 } } }, "_update_policy": { "total": 2478.597335201048, "count": 493, "self": 195.6742476248619, "children": { "TorchPOCAOptimizer.update": { "total": 2282.923087576186, "count": 14937, "self": 2282.923087576186 } } } } } } }, "trainer_threads": { "total": 7.780035957694054e-07, "count": 1, "self": 7.780035957694054e-07 }, "TrainerController._save_models": { "total": 3.183329606006737, "count": 1, "self": 0.17722880601650104, "children": { "RLTrainer._checkpoint": { "total": 3.006100799990236, "count": 1, "self": 3.006100799990236 } } } } } } }