{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.503925085067749, "min": 1.2870746850967407, "max": 3.2957651615142822, "count": 2643 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32581.033203125, "min": 3673.99755859375, "max": 105464.484375, "count": 2643 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.142857142857146, "min": 38.359375, "max": 999.0, "count": 2643 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 3996.0, "max": 30516.0, "count": 2643 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1721.2802988760939, "min": 1187.1543862478682, "max": 1740.170175564165, "count": 2568 }, "SoccerTwos.Self-play.ELO.sum": { "value": 313273.0143954491, "min": 2380.369359055664, "max": 409485.1632906863, "count": 2568 }, "SoccerTwos.Step.mean": { "value": 26429936.0, "min": 9274.0, "max": 26429936.0, "count": 2643 }, "SoccerTwos.Step.sum": { "value": 26429936.0, "min": 9274.0, "max": 26429936.0, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06270360946655273, "min": -0.13885830342769623, "max": 0.18183642625808716, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -11.474761009216309, "min": -23.88362693786621, "max": 28.002809524536133, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06207377091050148, "min": -0.1356102079153061, "max": 0.18300901353359222, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.35949993133545, "min": -23.588298797607422, "max": 28.183387756347656, "count": 2643 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2643 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06408524382961252, "min": -0.5377428574221474, "max": 0.44646154000208926, "count": 2643 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.727599620819092, "min": -64.78880047798157, "max": 59.410799741744995, "count": 2643 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06408524382961252, "min": -0.5377428574221474, "max": 0.44646154000208926, "count": 2643 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.727599620819092, "min": -64.78880047798157, "max": 59.410799741744995, "count": 2643 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2643 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2643 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015245851777338733, "min": 0.008800792263355107, "max": 0.025791054552731413, "count": 1277 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015245851777338733, "min": 0.008800792263355107, "max": 0.025791054552731413, "count": 1277 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10285454814632734, "min": 1.4963562714835157e-07, "max": 0.13516210541129112, "count": 1277 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10285454814632734, "min": 1.4963562714835157e-07, "max": 0.13516210541129112, "count": 1277 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10417892883221308, "min": 1.7443839558003069e-07, "max": 0.1369783416390419, "count": 1277 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10417892883221308, "min": 1.7443839558003069e-07, "max": 0.1369783416390419, "count": 1277 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1277 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1277 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1277 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1277 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1277 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1277 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695620799", "python_version": "3.9.18 (main, Sep 11 2023, 13:41:44) \n[GCC 11.2.0]", "command_line_arguments": "/home/genly/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695695757" }, "total": 74957.5998916002, "count": 1, "self": 0.37824017368257046, "children": { "run_training.setup": { "total": 0.013932876754552126, "count": 1, "self": 0.013932876754552126 }, "TrainerController.start_learning": { "total": 74957.20771854976, "count": 1, "self": 28.325114775449038, "children": { "TrainerController._reset_env": { "total": 3.6112374193035066, "count": 133, "self": 3.6112374193035066 }, "TrainerController.advance": { "total": 74924.97800013516, "count": 1819864, "self": 26.490538095124066, "children": { "env_step": { "total": 26447.454270750284, "count": 1819864, "self": 22078.23588775145, "children": { "SubprocessEnvManager._take_step": { "total": 4352.479857348371, "count": 1819864, "self": 161.50091971829534, "children": { "TorchPolicy.evaluate": { "total": 4190.978937630076, "count": 3326822, "self": 4190.978937630076 } } }, "workers": { "total": 16.738525650464, "count": 1819863, "self": 0.0, "children": { "worker_root": { "total": 74914.41346712876, "count": 1819863, "is_parallel": true, "self": 56305.386541230604, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002260328270494938, "count": 2, "is_parallel": true, "self": 0.00043610529974102974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018242229707539082, "count": 8, "is_parallel": true, "self": 0.0018242229707539082 } } }, "UnityEnvironment.step": { "total": 0.024057872127741575, "count": 1, "is_parallel": true, "self": 0.0007963343523442745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009081787429749966, "count": 1, "is_parallel": true, "self": 0.0009081787429749966 }, "communicator.exchange": { "total": 0.020508917048573494, "count": 1, "is_parallel": true, "self": 0.020508917048573494 }, "steps_from_proto": { "total": 0.0018444419838488102, "count": 2, "is_parallel": true, "self": 0.00036615971475839615, "children": { "_process_rank_one_or_two_observation": { "total": 0.001478282269090414, "count": 8, "is_parallel": true, "self": 0.001478282269090414 } } } } } } }, "UnityEnvironment.step": { "total": 18608.784390117973, "count": 1819862, "is_parallel": true, "self": 1090.4689699783921, "children": { "UnityEnvironment._generate_step_input": { "total": 696.5572505993769, "count": 1819862, "is_parallel": true, "self": 696.5572505993769 }, "communicator.exchange": { "total": 13802.903025161475, "count": 1819862, "is_parallel": true, "self": 13802.903025161475 }, "steps_from_proto": { "total": 3018.855144378729, "count": 3639724, "is_parallel": true, "self": 468.9475295683369, "children": { "_process_rank_one_or_two_observation": { "total": 2549.9076148103923, "count": 14558896, "is_parallel": true, "self": 2549.9076148103923 } } } } }, "steps_from_proto": { "total": 0.24253578018397093, "count": 264, "is_parallel": true, "self": 0.03884504083544016, "children": { "_process_rank_one_or_two_observation": { "total": 0.20369073934853077, "count": 1056, "is_parallel": true, "self": 0.20369073934853077 } } } } } } } } }, "trainer_advance": { "total": 48451.03319128975, "count": 1819863, "self": 244.69135109847412, "children": { "process_trajectory": { "total": 7197.596126302145, "count": 1819863, "self": 7184.11433515558, "children": { "RLTrainer._checkpoint": { "total": 13.481791146565229, "count": 52, "self": 13.481791146565229 } } }, "_update_policy": { "total": 41008.74571388913, "count": 1277, "self": 3996.2130596269853, "children": { "TorchPOCAOptimizer.update": { "total": 37012.53265426215, "count": 38322, "self": 37012.53265426215 } } } } } } }, "trainer_threads": { "total": 7.809139788150787e-07, "count": 1, "self": 7.809139788150787e-07 }, "TrainerController._save_models": { "total": 0.2933654389344156, "count": 1, "self": 0.0068657975643873215, "children": { "RLTrainer._checkpoint": { "total": 0.28649964137002826, "count": 1, "self": 0.28649964137002826 } } } } } } }