| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.1728253960609436, |
| "min": 0.16308020055294037, |
| "max": 1.4763644933700562, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5223.474609375, |
| "min": 4918.4990234375, |
| "max": 44786.9921875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999965.0, |
| "min": 29989.0, |
| "max": 2999965.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999965.0, |
| "min": 29989.0, |
| "max": 2999965.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.816712498664856, |
| "min": -0.203117236495018, |
| "max": 0.8835760354995728, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 243.3803253173828, |
| "min": -48.34190368652344, |
| "max": 274.7921447753906, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.019102422520518303, |
| "min": -0.01084805652499199, |
| "max": 0.29096683859825134, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.692522048950195, |
| "min": -3.2218728065490723, |
| "max": 69.25010681152344, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06926028755454658, |
| "min": 0.06432453564013399, |
| "max": 0.07469949284374403, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.969644025763652, |
| "min": 0.5052627934525645, |
| "max": 1.0601396428400596, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013062040997153548, |
| "min": 0.00012047082789129815, |
| "max": 0.01612036287102552, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.18286857396014966, |
| "min": 0.00151611503153783, |
| "max": 0.23745259088658105, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5193066364547668e-06, |
| "min": 1.5193066364547668e-06, |
| "max": 0.0002984122719578143, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.1270292910366736e-05, |
| "min": 2.1270292910366736e-05, |
| "max": 0.0037248839583720332, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1005064023809524, |
| "min": 0.1005064023809524, |
| "max": 0.19947075714285717, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4070896333333336, |
| "min": 1.3962953000000002, |
| "max": 2.677506533333333, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.058959785714302e-05, |
| "min": 6.058959785714302e-05, |
| "max": 0.009947128638571428, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008482543700000023, |
| "min": 0.0008482543700000023, |
| "max": 0.12416863387000002, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007786216679960489, |
| "min": 0.007055687252432108, |
| "max": 0.49347636103630066, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.10900703072547913, |
| "min": 0.1036483570933342, |
| "max": 3.4543344974517822, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 232.61029411764707, |
| "min": 204.62142857142857, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31635.0, |
| "min": 16532.0, |
| "max": 33809.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7232602783752715, |
| "min": -0.9998625526204705, |
| "max": 1.7953309267759323, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 234.36339785903692, |
| "min": -31.995601683855057, |
| "max": 249.5509988218546, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7232602783752715, |
| "min": -0.9998625526204705, |
| "max": 1.7953309267759323, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 234.36339785903692, |
| "min": -31.995601683855057, |
| "max": 249.5509988218546, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.018693804626924677, |
| "min": 0.015408162045394734, |
| "max": 9.614438253290514, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.542357429261756, |
| "min": 2.141734524309868, |
| "max": 163.44545030593872, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1768550416", |
| "python_version": "3.10.19 (main, Oct 21 2025, 16:43:05) [GCC 11.2.0]", |
| "command_line_arguments": "/home/ninghang/anaconda3/envs/qxh_huggy_env/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1768558905" |
| }, |
| "total": 8489.217343541328, |
| "count": 1, |
| "self": 0.5256404294632375, |
| "children": { |
| "run_training.setup": { |
| "total": 0.042277988977730274, |
| "count": 1, |
| "self": 0.042277988977730274 |
| }, |
| "TrainerController.start_learning": { |
| "total": 8488.649425122887, |
| "count": 1, |
| "self": 2.8993346840143204, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 5.75547471921891, |
| "count": 1, |
| "self": 5.75547471921891 |
| }, |
| "TrainerController.advance": { |
| "total": 8479.920919189695, |
| "count": 194912, |
| "self": 3.004710135050118, |
| "children": { |
| "env_step": { |
| "total": 6286.280644763727, |
| "count": 194912, |
| "self": 5900.9771484970115, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 383.55817039869726, |
| "count": 194912, |
| "self": 9.999258208088577, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 373.5589121906087, |
| "count": 187565, |
| "self": 373.5589121906087 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.7453258680179715, |
| "count": 194912, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 8478.26584891975, |
| "count": 194912, |
| "is_parallel": true, |
| "self": 2915.2074072700925, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0034880409948527813, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0010593901388347149, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0024286508560180664, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0024286508560180664 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.040600516833364964, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008473135530948639, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0007738666608929634, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007738666608929634 |
| }, |
| "communicator.exchange": { |
| "total": 0.03654577676206827, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03654577676206827 |
| }, |
| "steps_from_proto": { |
| "total": 0.0024335598573088646, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005511930212378502, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0018823668360710144, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0018823668360710144 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 5563.058441649657, |
| "count": 194911, |
| "is_parallel": true, |
| "self": 149.22693460341543, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 103.57292680395767, |
| "count": 194911, |
| "is_parallel": true, |
| "self": 103.57292680395767 |
| }, |
| "communicator.exchange": { |
| "total": 4892.346209367737, |
| "count": 194911, |
| "is_parallel": true, |
| "self": 4892.346209367737 |
| }, |
| "steps_from_proto": { |
| "total": 417.91237087454647, |
| "count": 194911, |
| "is_parallel": true, |
| "self": 86.86643951525912, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 331.04593135928735, |
| "count": 1559288, |
| "is_parallel": true, |
| "self": 331.04593135928735 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2190.6355642909184, |
| "count": 194912, |
| "self": 6.148625488393009, |
| "children": { |
| "process_trajectory": { |
| "total": 330.28213377436623, |
| "count": 194912, |
| "self": 329.8232858059928, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.45884796837344766, |
| "count": 6, |
| "self": 0.45884796837344766 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1854.2048050281592, |
| "count": 1390, |
| "self": 877.7893710983917, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 976.4154339297675, |
| "count": 68439, |
| "self": 976.4154339297675 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.690411388874054e-07, |
| "count": 1, |
| "self": 9.690411388874054e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07369556091725826, |
| "count": 1, |
| "self": 0.0011517140083014965, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07254384690895677, |
| "count": 1, |
| "self": 0.07254384690895677 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
