{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.082656741142273, "min": 1.082656741142273, "max": 2.850872039794922, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10396.7529296875, "min": 10396.7529296875, "max": 29533.806640625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.498281478881836, "min": 0.5068367719650269, "max": 13.498281478881836, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1363.326416015625, "min": 49.16316604614258, "max": 1363.326416015625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.73076923076923, "min": 3.8181818181818183, "max": 26.73076923076923, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1390.0, "min": 168.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.73076923076923, "min": 3.8181818181818183, "max": 26.73076923076923, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1390.0, "min": 168.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07048686181637916, "min": 0.06069070391525862, "max": 0.07250883245898662, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2819474472655166, "min": 0.2450090896015229, "max": 0.35657678011407634, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1856781611328616, "min": 0.11684669547842122, "max": 0.3163380953026753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7427126445314464, "min": 0.4673867819136849, "max": 1.5816904765133766, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3250097350000015e-05, "min": 1.3250097350000015e-05, "max": 0.00048625000275, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.300038940000006e-05, "min": 5.300038940000006e-05, "max": 0.0023075000384999997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10265, "min": 0.10265, "max": 0.19725000000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4106, "min": 0.4106, "max": 0.9615, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014223500000000013, "min": 0.00014223500000000013, "max": 0.004862775, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005689400000000005, "min": 0.0005689400000000005, "max": 0.023078849999999998, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678288014", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678288554" }, "total": 539.8902899520001, "count": 1, "self": 0.48659398500001316, "children": { "run_training.setup": { "total": 0.13531902700003684, "count": 1, "self": 0.13531902700003684 }, "TrainerController.start_learning": { "total": 539.26837694, "count": 1, "self": 0.7281902009981422, "children": { "TrainerController._reset_env": { "total": 9.285215144000006, "count": 1, "self": 9.285215144000006 }, "TrainerController.advance": { "total": 529.0831551470019, "count": 18214, "self": 0.3710974269985172, "children": { "env_step": { "total": 528.7120577200034, "count": 18214, "self": 340.85046768900906, "children": { "SubprocessEnvManager._take_step": { "total": 187.51230437598758, "count": 18214, "self": 1.8478902439886724, "children": { "TorchPolicy.evaluate": { "total": 185.6644141319989, "count": 18214, "self": 38.449853137996115, "children": { "TorchPolicy.sample_actions": { "total": 147.2145609940028, "count": 18214, "self": 147.2145609940028 } } } } }, "workers": { "total": 0.3492856550067245, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 537.0978472369882, "count": 18214, "is_parallel": true, "self": 259.7609654429866, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0069023339999603195, "count": 1, "is_parallel": true, "self": 0.005481708999980128, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014206249999801912, "count": 10, "is_parallel": true, "self": 0.0014206249999801912 } } }, "UnityEnvironment.step": { "total": 0.03775866199998745, "count": 1, "is_parallel": true, "self": 0.0006280879999849276, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005351620000055846, "count": 1, "is_parallel": true, "self": 0.0005351620000055846 }, "communicator.exchange": { "total": 0.03443879700000707, "count": 1, "is_parallel": true, "self": 0.03443879700000707 }, "steps_from_proto": { "total": 0.00215661499998987, "count": 1, "is_parallel": true, "self": 0.0006182680000392793, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015383469999505905, "count": 10, "is_parallel": true, "self": 0.0015383469999505905 } } } } } } }, "UnityEnvironment.step": { "total": 277.33688179400156, "count": 18213, "is_parallel": true, "self": 11.228341217000661, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8870297150026545, "count": 18213, "is_parallel": true, "self": 5.8870297150026545 }, "communicator.exchange": { "total": 224.14853261000553, "count": 18213, "is_parallel": true, "self": 224.14853261000553 }, "steps_from_proto": { "total": 36.07297825199271, "count": 18213, "is_parallel": true, "self": 8.42285203299275, "children": { "_process_rank_one_or_two_observation": { "total": 27.650126218999958, "count": 182130, "is_parallel": true, "self": 27.650126218999958 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002312520000486984, "count": 1, "self": 0.0002312520000486984, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 526.0584329470565, "count": 354443, "is_parallel": true, "self": 9.57292008206116, "children": { "process_trajectory": { "total": 257.52925828799494, "count": 354443, "is_parallel": true, "self": 255.86326507999513, "children": { "RLTrainer._checkpoint": { "total": 1.6659932079998043, "count": 4, "is_parallel": true, "self": 1.6659932079998043 } } }, "_update_policy": { "total": 258.95625457700044, "count": 90, "is_parallel": true, "self": 78.21131329200216, "children": { "TorchPPOOptimizer.update": { "total": 180.74494128499828, "count": 4590, "is_parallel": true, "self": 180.74494128499828 } } } } } } } } }, "TrainerController._save_models": { "total": 0.17158519600002364, "count": 1, "self": 0.0009031579998008965, "children": { "RLTrainer._checkpoint": { "total": 0.17068203800022275, "count": 1, "self": 0.17068203800022275 } } } } } } }