{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8201637864112854, "min": 0.8201637864112854, "max": 2.8536489009857178, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7830.923828125, "min": 7830.923828125, "max": 29286.998046875, "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": 12.813446044921875, "min": 0.5901376008987427, "max": 12.813446044921875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.6220703125, "min": 114.4866943359375, "max": 2613.1357421875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.064219513382519, "min": 0.06170255742182128, "max": 0.07479724663537449, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.256878053530076, "min": 0.2468102296872851, "max": 0.3739862331768724, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19774005251626173, "min": 0.144123618602844, "max": 0.30456199587560173, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7909602100650469, "min": 0.576494474411376, "max": 1.5228099793780085, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.727272727272727, "min": 4.295454545454546, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 189.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 4.295454545454546, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 189.0, "max": 1381.0, "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": "1687477012", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1687477510" }, "total": 498.20818008, "count": 1, "self": 0.8399295019999045, "children": { "run_training.setup": { "total": 0.06067696100001285, "count": 1, "self": 0.06067696100001285 }, "TrainerController.start_learning": { "total": 497.30757361700006, "count": 1, "self": 0.5903455250008278, "children": { "TrainerController._reset_env": { "total": 5.013150362999966, "count": 1, "self": 5.013150362999966 }, "TrainerController.advance": { "total": 491.45374105499917, "count": 18210, "self": 0.2726372689960499, "children": { "env_step": { "total": 491.1811037860031, "count": 18210, "self": 357.92219203702234, "children": { "SubprocessEnvManager._take_step": { "total": 132.9826643369866, "count": 18210, "self": 1.9371000079947294, "children": { "TorchPolicy.evaluate": { "total": 131.04556432899187, "count": 18210, "self": 131.04556432899187 } } }, "workers": { "total": 0.27624741199417713, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 495.6711082239893, "count": 18210, "is_parallel": true, "self": 233.71948573598456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006316492999985712, "count": 1, "is_parallel": true, "self": 0.004178623000029802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021378699999559103, "count": 10, "is_parallel": true, "self": 0.0021378699999559103 } } }, "UnityEnvironment.step": { "total": 0.03707935099998849, "count": 1, "is_parallel": true, "self": 0.0005677619998891714, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003415720000248257, "count": 1, "is_parallel": true, "self": 0.0003415720000248257 }, "communicator.exchange": { "total": 0.034176846000036676, "count": 1, "is_parallel": true, "self": 0.034176846000036676 }, "steps_from_proto": { "total": 0.001993171000037819, "count": 1, "is_parallel": true, "self": 0.0003612370000496412, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016319339999881777, "count": 10, "is_parallel": true, "self": 0.0016319339999881777 } } } } } } }, "UnityEnvironment.step": { "total": 261.9516224880047, "count": 18209, "is_parallel": true, "self": 10.812940709010093, "children": { "UnityEnvironment._generate_step_input": { "total": 5.611366643997542, "count": 18209, "is_parallel": true, "self": 5.611366643997542 }, "communicator.exchange": { "total": 207.4296788209906, "count": 18209, "is_parallel": true, "self": 207.4296788209906 }, "steps_from_proto": { "total": 38.09763631400648, "count": 18209, "is_parallel": true, "self": 6.993340424031317, "children": { "_process_rank_one_or_two_observation": { "total": 31.104295889975162, "count": 182090, "is_parallel": true, "self": 31.104295889975162 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012498500007041002, "count": 1, "self": 0.00012498500007041002, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.6035857519574, "count": 472499, "is_parallel": true, "self": 10.54128627096054, "children": { "process_trajectory": { "total": 268.68816841999694, "count": 472499, "is_parallel": true, "self": 266.9973767639969, "children": { "RLTrainer._checkpoint": { "total": 1.6907916560000444, "count": 4, "is_parallel": true, "self": 1.6907916560000444 } } }, "_update_policy": { "total": 208.3741310609999, "count": 90, "is_parallel": true, "self": 81.92587444299846, "children": { "TorchPPOOptimizer.update": { "total": 126.44825661800144, "count": 4584, "is_parallel": true, "self": 126.44825661800144 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2502116890000252, "count": 1, "self": 0.0011395160000802207, "children": { "RLTrainer._checkpoint": { "total": 0.249072172999945, "count": 1, "self": 0.249072172999945 } } } } } } }