{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4932351112365723, "min": 2.4932351112365723, "max": 3.295762777328491, "count": 301 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55449.546875, "min": 15175.5185546875, "max": 108702.859375, "count": 301 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.955555555555556, "min": 46.666666666666664, "max": 999.0, "count": 301 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19784.0, "min": 15564.0, "max": 25516.0, "count": 301 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1424.2568962525577, "min": 1198.381890849238, "max": 1425.7131067735204, "count": 255 }, "SoccerTwos.Self-play.ELO.sum": { "value": 256366.24132546037, "min": 2400.034436562306, "max": 293703.9598943941, "count": 255 }, "SoccerTwos.Step.mean": { "value": 3009990.0, "min": 9774.0, "max": 3009990.0, "count": 301 }, "SoccerTwos.Step.sum": { "value": 3009990.0, "min": 9774.0, "max": 3009990.0, "count": 301 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03920089825987816, "min": -0.05091611668467522, "max": 0.19523094594478607, "count": 301 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.016960620880127, "min": -10.030474662780762, "max": 20.29961585998535, "count": 301 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03831464424729347, "min": -0.051254600286483765, "max": 0.2010337859392166, "count": 301 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.858321189880371, "min": -10.097156524658203, "max": 21.403934478759766, "count": 301 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 301 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 301 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08670391317186409, "min": -0.6047799976542592, "max": 0.5424400006021772, "count": 301 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.520000457763672, "min": -45.38840043544769, "max": 41.24939972162247, "count": 301 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08670391317186409, "min": -0.6047799976542592, "max": 0.5424400006021772, "count": 301 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.520000457763672, "min": -45.38840043544769, "max": 41.24939972162247, "count": 301 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 301 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 301 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019933591484247396, "min": 0.0102610221428525, "max": 0.022171040313939253, "count": 142 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019933591484247396, "min": 0.0102610221428525, "max": 0.022171040313939253, "count": 142 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08567158604661623, "min": 3.67103888265774e-07, "max": 0.09261030455430348, "count": 142 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08567158604661623, "min": 3.67103888265774e-07, "max": 0.09261030455430348, "count": 142 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08662142530083657, "min": 5.43677314605399e-07, "max": 0.094602270424366, "count": 142 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08662142530083657, "min": 5.43677314605399e-07, "max": 0.094602270424366, "count": 142 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 142 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 142 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 142 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 142 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 142 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 142 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676200733", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/numanmohammad/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_4 --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": "1676217623" }, "total": 16889.386610081, "count": 1, "self": 0.5301684959995328, "children": { "run_training.setup": { "total": 0.055927148999999954, "count": 1, "self": 0.055927148999999954 }, "TrainerController.start_learning": { "total": 16888.800514436003, "count": 1, "self": 6.057592861558078, "children": { "TrainerController._reset_env": { "total": 4.030374796997214, "count": 16, "self": 4.030374796997214 }, "TrainerController.advance": { "total": 16878.280215613453, "count": 198148, "self": 6.3010103682026966, "children": { "env_step": { "total": 4678.166740248991, "count": 198148, "self": 3832.033327977566, "children": { "SubprocessEnvManager._take_step": { "total": 842.3676424640794, "count": 198148, "self": 42.37373407699647, "children": { "TorchPolicy.evaluate": { "total": 799.9939083870829, "count": 383684, "self": 799.9939083870829 } } }, "workers": { "total": 3.765769807345876, "count": 198147, "self": 0.0, "children": { "worker_root": { "total": 16874.310074276, "count": 198147, "is_parallel": true, "self": 13763.786149159852, "children": { "steps_from_proto": { "total": 0.041061649997048644, "count": 32, "is_parallel": true, "self": 0.00884137500270965, "children": { "_process_rank_one_or_two_observation": { "total": 0.03222027499433899, "count": 128, "is_parallel": true, "self": 0.03222027499433899 } } }, "UnityEnvironment.step": { "total": 3110.4828634661503, "count": 198147, "is_parallel": true, "self": 173.0467596460535, "children": { "UnityEnvironment._generate_step_input": { "total": 117.55066479009602, "count": 198147, "is_parallel": true, "self": 117.55066479009602 }, "communicator.exchange": { "total": 2292.3341577065876, "count": 198147, "is_parallel": true, "self": 2292.3341577065876 }, "steps_from_proto": { "total": 527.5512813234134, "count": 396294, "is_parallel": true, "self": 113.85399624045453, "children": { "_process_rank_one_or_two_observation": { "total": 413.69728508295884, "count": 1585176, "is_parallel": true, "self": 413.69728508295884 } } } } } } } } } } }, "trainer_advance": { "total": 12193.81246499626, "count": 198147, "self": 40.42644453520188, "children": { "process_trajectory": { "total": 1284.6019422140507, "count": 198147, "self": 1282.157113324051, "children": { "RLTrainer._checkpoint": { "total": 2.444828889999826, "count": 6, "self": 2.444828889999826 } } }, "_update_policy": { "total": 10868.784078247007, "count": 142, "self": 640.584827876004, "children": { "TorchPOCAOptimizer.update": { "total": 10228.199250371003, "count": 4260, "self": 10228.199250371003 } } } } } } }, "trainer_threads": { "total": 5.218997102929279e-06, "count": 1, "self": 5.218997102929279e-06 }, "TrainerController._save_models": { "total": 0.4323259449993202, "count": 1, "self": 0.0021620840016112197, "children": { "RLTrainer._checkpoint": { "total": 0.430163860997709, "count": 1, "self": 0.430163860997709 } } } } } } }