{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.449774980545044, "min": 1.3487062454223633, "max": 3.2957112789154053, "count": 1712 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29784.177734375, "min": 22025.048828125, "max": 127799.4296875, "count": 1712 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.9010989010989, "min": 42.4, "max": 999.0, "count": 1712 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19620.0, "min": 13552.0, "max": 28056.0, "count": 1712 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1714.6954441310768, "min": 1195.4577594768393, "max": 1729.4800631598341, "count": 1649 }, "SoccerTwos.Self-play.ELO.sum": { "value": 312074.570831856, "min": 2394.412484963762, "max": 371230.66129604285, "count": 1649 }, "SoccerTwos.Step.mean": { "value": 17119927.0, "min": 9046.0, "max": 17119927.0, "count": 1712 }, "SoccerTwos.Step.sum": { "value": 17119927.0, "min": 9046.0, "max": 17119927.0, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03298421949148178, "min": -0.1342843621969223, "max": 0.14929881691932678, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.0031280517578125, "min": -20.105175018310547, "max": 25.184162139892578, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.030438734218478203, "min": -0.14658209681510925, "max": 0.15797609090805054, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.539849758148193, "min": -20.228328704833984, "max": 24.80224609375, "count": 1712 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1712 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.11100439612682049, "min": -0.5801428584825425, "max": 0.3921764703357921, "count": 1712 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.20280009508133, "min": -62.30199992656708, "max": 59.65120041370392, "count": 1712 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.11100439612682049, "min": -0.5801428584825425, "max": 0.3921764703357921, "count": 1712 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.20280009508133, "min": -62.30199992656708, "max": 59.65120041370392, "count": 1712 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1712 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1712 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015179576117467756, "min": 0.01009599030391352, "max": 0.02409853325225413, "count": 824 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015179576117467756, "min": 0.01009599030391352, "max": 0.02409853325225413, "count": 824 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10501042852799097, "min": 3.019063920343494e-07, "max": 0.12999793688456218, "count": 824 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10501042852799097, "min": 3.019063920343494e-07, "max": 0.12999793688456218, "count": 824 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10629602844516436, "min": 2.915903247450539e-07, "max": 0.1321681447327137, "count": 824 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10629602844516436, "min": 2.915903247450539e-07, "max": 0.1321681447327137, "count": 824 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 824 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 824 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 824 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 824 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 824 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 824 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680813518", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/margarita/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=/Users/margarita/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --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": "1680880620" }, "total": 67101.769653542, "count": 1, "self": 0.4097942930093268, "children": { "run_training.setup": { "total": 0.019266541000000026, "count": 1, "self": 0.019266541000000026 }, "TrainerController.start_learning": { "total": 67101.34059270799, "count": 1, "self": 13.524889400883694, "children": { "TrainerController._reset_env": { "total": 6.832727633034846, "count": 86, "self": 6.832727633034846 }, "TrainerController.advance": { "total": 67080.89591046606, "count": 1167525, "self": 11.79990935177193, "children": { "env_step": { "total": 53675.59226013494, "count": 1167525, "self": 51863.03611767621, "children": { "SubprocessEnvManager._take_step": { "total": 1803.520905126439, "count": 1167525, "self": 53.666242776936315, "children": { "TorchPolicy.evaluate": { "total": 1749.8546623495026, "count": 2164000, "self": 1749.8546623495026 } } }, "workers": { "total": 9.035237332286467, "count": 1167524, "self": 0.0, "children": { "worker_root": { "total": 67074.64384416582, "count": 1167524, "is_parallel": true, "self": 16733.83932746815, "children": { "steps_from_proto": { "total": 0.1397440380091468, "count": 172, "is_parallel": true, "self": 0.014730041952381256, "children": { "_process_rank_one_or_two_observation": { "total": 0.12501399605676555, "count": 688, "is_parallel": true, "self": 0.12501399605676555 } } }, "UnityEnvironment.step": { "total": 50340.664772659664, "count": 1167524, "is_parallel": true, "self": 140.5281040196205, "children": { "UnityEnvironment._generate_step_input": { "total": 905.3984929642213, "count": 1167524, "is_parallel": true, "self": 905.3984929642213 }, "communicator.exchange": { "total": 47292.84596446135, "count": 1167524, "is_parallel": true, "self": 47292.84596446135 }, "steps_from_proto": { "total": 2001.8922112144726, "count": 2335048, "is_parallel": true, "self": 208.63691510042804, "children": { "_process_rank_one_or_two_observation": { "total": 1793.2552961140445, "count": 9340192, "is_parallel": true, "self": 1793.2552961140445 } } } } } } } } } } }, "trainer_advance": { "total": 13393.503740979355, "count": 1167524, "self": 100.4404484370807, "children": { "process_trajectory": { "total": 2487.652892616354, "count": 1167524, "self": 2484.0921254493624, "children": { "RLTrainer._checkpoint": { "total": 3.5607671669915817, "count": 34, "self": 3.5607671669915817 } } }, "_update_policy": { "total": 10805.41039992592, "count": 824, "self": 1345.473841031786, "children": { "TorchPOCAOptimizer.update": { "total": 9459.936558894135, "count": 24720, "self": 9459.936558894135 } } } } } } }, "trainer_threads": { "total": 4.580069798976183e-07, "count": 1, "self": 4.580069798976183e-07 }, "TrainerController._save_models": { "total": 0.08706474999780767, "count": 1, "self": 0.0008219580049626529, "children": { "RLTrainer._checkpoint": { "total": 0.08624279199284501, "count": 1, "self": 0.08624279199284501 } } } } } } }