{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1249186992645264, "min": 3.1023879051208496, "max": 3.2957534790039062, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28599.255859375, "min": 15383.267578125, "max": 156816.921875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 832.1666666666666, "min": 272.77777777777777, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19972.0, "min": 5156.0, "max": 28748.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1218.463314003117, "min": 1194.9429334358551, "max": 1225.964117543023, "count": 345 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9747.706512024935, "min": 2389.8858668717103, "max": 39090.16441065677, "count": 345 }, "SoccerTwos.Step.mean": { "value": 4999098.0, "min": 9394.0, "max": 4999098.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999098.0, "min": 9394.0, "max": 4999098.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008336874656379223, "min": -0.014455064199864864, "max": 0.027775796130299568, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.10004249215126038, "min": -0.39028674364089966, "max": 0.41663694381713867, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.008533528074622154, "min": -0.015282760374248028, "max": 0.027741296216845512, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.10240233689546585, "min": -0.3585999310016632, "max": 0.41611945629119873, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.20611666639645895, "min": -0.7223826076673425, "max": 0.44031111233764225, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.4733999967575073, "min": -16.614799976348877, "max": 10.413199961185455, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.20611666639645895, "min": -0.7223826076673425, "max": 0.44031111233764225, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.4733999967575073, "min": -16.614799976348877, "max": 10.413199961185455, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015365945894639783, "min": 0.010205141287830581, "max": 0.023643144588762273, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015365945894639783, "min": 0.010205141287830581, "max": 0.023643144588762273, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0076258563591788215, "min": 2.4769114818449604e-08, "max": 0.00910759853820006, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0076258563591788215, "min": 2.4769114818449604e-08, "max": 0.00910759853820006, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.007699296902865171, "min": 1.8153060565850864e-08, "max": 0.009323406747231882, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.007699296902865171, "min": 1.8153060565850864e-08, "max": 0.009323406747231882, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723376269", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/home/arunachalam/rl-agents/agents-env/bin/mlagents-learn ./config/Soccer2player.yaml --env=./training-env-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723390301" }, "total": 14032.629968817004, "count": 1, "self": 2.1376076599990483, "children": { "run_training.setup": { "total": 0.009511717002169462, "count": 1, "self": 0.009511717002169462 }, "TrainerController.start_learning": { "total": 14030.482849440003, "count": 1, "self": 6.223035381401132, "children": { "TrainerController._reset_env": { "total": 5.502213287010818, "count": 25, "self": 5.502213287010818 }, "TrainerController.advance": { "total": 14018.386988909595, "count": 325177, "self": 7.445543163314142, "children": { "env_step": { "total": 5811.877426455721, "count": 325177, "self": 4525.175247842737, "children": { "SubprocessEnvManager._take_step": { "total": 1282.1815960891036, "count": 325177, "self": 50.21678608264483, "children": { "TorchPolicy.evaluate": { "total": 1231.9648100064587, "count": 645138, "self": 1231.9648100064587 } } }, "workers": { "total": 4.520582523880876, "count": 325177, "self": 0.0, "children": { "worker_root": { "total": 14018.839571044471, "count": 325177, "is_parallel": true, "self": 10324.883514666533, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017830469987529796, "count": 2, "is_parallel": true, "self": 0.0004381180006021168, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013449289981508628, "count": 8, "is_parallel": true, "self": 0.0013449289981508628 } } }, "UnityEnvironment.step": { "total": 0.029157692999433493, "count": 1, "is_parallel": true, "self": 0.0007788169968989678, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0016391909994126763, "count": 1, "is_parallel": true, "self": 0.0016391909994126763 }, "communicator.exchange": { "total": 0.02444483900035266, "count": 1, "is_parallel": true, "self": 0.02444483900035266 }, "steps_from_proto": { "total": 0.002294846002769191, "count": 2, "is_parallel": true, "self": 0.0004378710036689881, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018569749991002027, "count": 8, "is_parallel": true, "self": 0.0018569749991002027 } } } } } } }, "UnityEnvironment.step": { "total": 3693.9236704689356, "count": 325176, "is_parallel": true, "self": 228.1241314480685, "children": { "UnityEnvironment._generate_step_input": { "total": 188.81007460401452, "count": 325176, "is_parallel": true, "self": 188.81007460401452 }, "communicator.exchange": { "total": 2613.135058785261, "count": 325176, "is_parallel": true, "self": 2613.135058785261 }, "steps_from_proto": { "total": 663.8544056315914, "count": 650352, "is_parallel": true, "self": 126.36630100009279, "children": { "_process_rank_one_or_two_observation": { "total": 537.4881046314986, "count": 2601408, "is_parallel": true, "self": 537.4881046314986 } } } } }, "steps_from_proto": { "total": 0.03238590900218696, "count": 48, "is_parallel": true, "self": 0.006737916010024492, "children": { "_process_rank_one_or_two_observation": { "total": 0.02564799299216247, "count": 192, "is_parallel": true, "self": 0.02564799299216247 } } } } } } } } }, "trainer_advance": { "total": 8199.06401929056, "count": 325177, "self": 57.65157899947735, "children": { "process_trajectory": { "total": 1019.5925448150774, "count": 325177, "self": 1013.7635504400787, "children": { "RLTrainer._checkpoint": { "total": 5.828994374998729, "count": 10, "self": 5.828994374998729 } } }, "_update_policy": { "total": 7121.819895476005, "count": 232, "self": 583.2135720981714, "children": { "TorchPOCAOptimizer.update": { "total": 6538.606323377833, "count": 6969, "self": 6538.606323377833 } } } } } } }, "trainer_threads": { "total": 7.989947334863245e-07, "count": 1, "self": 7.989947334863245e-07 }, "TrainerController._save_models": { "total": 0.3706110630009789, "count": 1, "self": 0.08323866900173016, "children": { "RLTrainer._checkpoint": { "total": 0.28737239399924874, "count": 1, "self": 0.28737239399924874 } } } } } } }