{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8891504406929016, "min": 0.8891504406929016, "max": 2.8648669719696045, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8518.9501953125, "min": 8518.9501953125, "max": 29496.669921875, "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": 12.803558349609375, "min": 0.4308902621269226, "max": 12.890036582946777, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.69384765625, "min": 83.59271240234375, "max": 2629.5673828125, "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.Losses.PolicyLoss.mean": { "value": 0.06844916743626955, "min": 0.06423062650012036, "max": 0.07522227079978479, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2737966697450782, "min": 0.25955876103156095, "max": 0.3761113539989239, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1994301993765083, "min": 0.12640536090076043, "max": 0.27862420444395025, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7977207975060332, "min": 0.5056214436030417, "max": 1.2841691810126399, "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": 25.34090909090909, "min": 3.5, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 154.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.5, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 154.0, "max": 1387.0, "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": "1684684757", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684685144" }, "total": 387.1055667160001, "count": 1, "self": 0.37760557100023107, "children": { "run_training.setup": { "total": 0.04572087199994712, "count": 1, "self": 0.04572087199994712 }, "TrainerController.start_learning": { "total": 386.68224027299993, "count": 1, "self": 0.6171887179948499, "children": { "TrainerController._reset_env": { "total": 0.8187751629998274, "count": 1, "self": 0.8187751629998274 }, "TrainerController.advance": { "total": 385.10458050000534, "count": 18206, "self": 0.29371727298030237, "children": { "env_step": { "total": 384.81086322702504, "count": 18206, "self": 307.64152454803957, "children": { "SubprocessEnvManager._take_step": { "total": 76.88839465898741, "count": 18206, "self": 1.494577511989064, "children": { "TorchPolicy.evaluate": { "total": 75.39381714699834, "count": 18206, "self": 75.39381714699834 } } }, "workers": { "total": 0.28094401999805996, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 385.78574652900784, "count": 18206, "is_parallel": true, "self": 173.87862612899062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024361370001315663, "count": 1, "is_parallel": true, "self": 0.0007090160002007906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017271209999307757, "count": 10, "is_parallel": true, "self": 0.0017271209999307757 } } }, "UnityEnvironment.step": { "total": 0.028771873000096093, "count": 1, "is_parallel": true, "self": 0.00042748600026243366, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030819499988865573, "count": 1, "is_parallel": true, "self": 0.00030819499988865573 }, "communicator.exchange": { "total": 0.026699048999944353, "count": 1, "is_parallel": true, "self": 0.026699048999944353 }, "steps_from_proto": { "total": 0.0013371430000006512, "count": 1, "is_parallel": true, "self": 0.0002564929998243315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010806500001763197, "count": 10, "is_parallel": true, "self": 0.0010806500001763197 } } } } } } }, "UnityEnvironment.step": { "total": 211.90712040001722, "count": 18205, "is_parallel": true, "self": 7.533496866034966, "children": { "UnityEnvironment._generate_step_input": { "total": 3.9483665670022674, "count": 18205, "is_parallel": true, "self": 3.9483665670022674 }, "communicator.exchange": { "total": 177.5841778609954, "count": 18205, "is_parallel": true, "self": 177.5841778609954 }, "steps_from_proto": { "total": 22.84107910598459, "count": 18205, "is_parallel": true, "self": 4.489291230976278, "children": { "_process_rank_one_or_two_observation": { "total": 18.351787875008313, "count": 182050, "is_parallel": true, "self": 18.351787875008313 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000222885000084716, "count": 1, "self": 0.000222885000084716, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 384.4261693989213, "count": 173193, "is_parallel": true, "self": 3.3599927458492402, "children": { "process_trajectory": { "total": 215.8114615480713, "count": 173193, "is_parallel": true, "self": 214.96743619207177, "children": { "RLTrainer._checkpoint": { "total": 0.8440253559995199, "count": 4, "is_parallel": true, "self": 0.8440253559995199 } } }, "_update_policy": { "total": 165.25471510500074, "count": 90, "is_parallel": true, "self": 47.41031491699937, "children": { "TorchPPOOptimizer.update": { "total": 117.84440018800137, "count": 4587, "is_parallel": true, "self": 117.84440018800137 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14147300699983134, "count": 1, "self": 0.0010126610000043001, "children": { "RLTrainer._checkpoint": { "total": 0.14046034599982704, "count": 1, "self": 0.14046034599982704 } } } } } } }