{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.04665207862854, "min": 1.04665207862854, "max": 2.8608298301696777, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10004.947265625, "min": 10004.947265625, "max": 29329.2265625, "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": 12.727492332458496, "min": 0.34032687544822693, "max": 12.727492332458496, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.861083984375, "min": 66.0234146118164, "max": 2587.1064453125, "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": 0.0667402584177919, "min": 0.062058399265808084, "max": 0.07176591393477329, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2669610336711676, "min": 0.24823359706323234, "max": 0.3556150603447653, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20046064710500194, "min": 0.1253127302385538, "max": 0.29302296843014514, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8018425884200078, "min": 0.5012509209542152, "max": 1.4651148421507256, "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": 24.954545454545453, "min": 3.5454545454545454, "max": 25.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 156.0, "max": 1376.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.5454545454545454, "max": 25.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 156.0, "max": 1376.0, "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": "1674557288", "python_version": "3.8.10 (default, Jun 22 2022, 20:18:18) \n[GCC 9.4.0]", "command_line_arguments": "/home/acl/Desktop/robot-learning/huggingface/5.ml-agents/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": "1.20.0", "end_time_seconds": "1674557843" }, "total": 554.6226232390002, "count": 1, "self": 0.21765753900012896, "children": { "run_training.setup": { "total": 0.012760378999928434, "count": 1, "self": 0.012760378999928434 }, "TrainerController.start_learning": { "total": 554.3922053210001, "count": 1, "self": 0.3610927399990942, "children": { "TrainerController._reset_env": { "total": 2.529548350999903, "count": 1, "self": 2.529548350999903 }, "TrainerController.advance": { "total": 551.4319443060015, "count": 18204, "self": 0.16515566099656098, "children": { "env_step": { "total": 551.2667886450049, "count": 18204, "self": 487.3885862689972, "children": { "SubprocessEnvManager._take_step": { "total": 63.71568237498923, "count": 18204, "self": 0.7577355379701203, "children": { "TorchPolicy.evaluate": { "total": 62.95794683701911, "count": 18204, "self": 11.590467134034043, "children": { "TorchPolicy.sample_actions": { "total": 51.367479702985065, "count": 18204, "self": 51.367479702985065 } } } } }, "workers": { "total": 0.16252000101849262, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 553.8153888100121, "count": 18204, "is_parallel": true, "self": 106.44602656602115, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008451670000795275, "count": 1, "is_parallel": true, "self": 0.00023706599972683762, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006081010003526899, "count": 10, "is_parallel": true, "self": 0.0006081010003526899 } } }, "UnityEnvironment.step": { "total": 0.03506900100001076, "count": 1, "is_parallel": true, "self": 0.00014083199994274764, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036305499997979496, "count": 1, "is_parallel": true, "self": 0.00036305499997979496 }, "communicator.exchange": { "total": 0.03363222699999824, "count": 1, "is_parallel": true, "self": 0.03363222699999824 }, "steps_from_proto": { "total": 0.0009328870000899769, "count": 1, "is_parallel": true, "self": 0.00020915100026286382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007237359998271131, "count": 10, "is_parallel": true, "self": 0.0007237359998271131 } } } } } } }, "UnityEnvironment.step": { "total": 447.36936224399096, "count": 18203, "is_parallel": true, "self": 1.7963448340278774, "children": { "UnityEnvironment._generate_step_input": { "total": 6.178324919977285, "count": 18203, "is_parallel": true, "self": 6.178324919977285 }, "communicator.exchange": { "total": 426.14824777599165, "count": 18203, "is_parallel": true, "self": 426.14824777599165 }, "steps_from_proto": { "total": 13.246444713994151, "count": 18203, "is_parallel": true, "self": 3.1611792790338313, "children": { "_process_rank_one_or_two_observation": { "total": 10.08526543496032, "count": 182030, "is_parallel": true, "self": 10.08526543496032 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011883099978149403, "count": 1, "self": 0.00011883099978149403, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 551.1977957340255, "count": 153102, "is_parallel": true, "self": 1.6086451371193107, "children": { "process_trajectory": { "total": 347.8816734169063, "count": 153102, "is_parallel": true, "self": 346.9233056969065, "children": { "RLTrainer._checkpoint": { "total": 0.9583677199998419, "count": 4, "is_parallel": true, "self": 0.9583677199998419 } } }, "_update_policy": { "total": 201.70747717999984, "count": 90, "is_parallel": true, "self": 24.64531184501402, "children": { "TorchPPOOptimizer.update": { "total": 177.06216533498582, "count": 4587, "is_parallel": true, "self": 177.06216533498582 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06950109299987162, "count": 1, "self": 0.0005247349999990547, "children": { "RLTrainer._checkpoint": { "total": 0.06897635799987256, "count": 1, "self": 0.06897635799987256 } } } } } } }