| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.8429846167564392, |
| "min": 0.8429846167564392, |
| "max": 1.502804160118103, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 25289.5390625, |
| "min": 25289.5390625, |
| "max": 45589.06640625, |
| "count": 17 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 509882.0, |
| "min": 29952.0, |
| "max": 509882.0, |
| "count": 17 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 509882.0, |
| "min": 29952.0, |
| "max": 509882.0, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.3478340208530426, |
| "min": -0.08725451678037643, |
| "max": 0.35829678177833557, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 90.43684387207031, |
| "min": -21.028339385986328, |
| "max": 93.15716552734375, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.03225788101553917, |
| "min": 0.018812665715813637, |
| "max": 0.28176987171173096, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 8.387048721313477, |
| "min": 4.834855079650879, |
| "max": 66.77945709228516, |
| "count": 17 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06887973945136071, |
| "min": 0.06583450421198865, |
| "max": 0.07254255880087727, |
| "count": 17 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9643163523190499, |
| "min": 0.495612762338514, |
| "max": 1.0409129210553751, |
| "count": 17 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.011578065592835802, |
| "min": 0.0007586126401399092, |
| "max": 0.011578065592835802, |
| "count": 17 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.1620929182997012, |
| "min": 0.010620576961958728, |
| "max": 0.1620929182997012, |
| "count": 17 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00025050805221160714, |
| "min": 0.00025050805221160714, |
| "max": 0.00029838354339596195, |
| "count": 17 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0035071127309625, |
| "min": 0.0020886848037717336, |
| "max": 0.0039694597768467664, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.1835026785714286, |
| "min": 0.1835026785714286, |
| "max": 0.19946118095238097, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.5690375000000003, |
| "min": 1.3962282666666668, |
| "max": 2.812430733333333, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.008351917589285714, |
| "min": 0.008351917589285714, |
| "max": 0.009946171977142856, |
| "count": 17 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.11692684625, |
| "min": 0.06962320384, |
| "max": 0.13232300801000002, |
| "count": 17 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.01609208807349205, |
| "min": 0.01609208807349205, |
| "max": 0.37398189306259155, |
| "count": 17 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.2252892404794693, |
| "min": 0.2252892404794693, |
| "max": 2.617873191833496, |
| "count": 17 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 515.8983050847457, |
| "min": 515.8983050847457, |
| "max": 999.0, |
| "count": 17 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30438.0, |
| "min": 15984.0, |
| "max": 32940.0, |
| "count": 17 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.2128575999858016, |
| "min": -1.0000000521540642, |
| "max": 1.2128575999858016, |
| "count": 17 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 71.55859839916229, |
| "min": -30.331601656973362, |
| "max": 71.55859839916229, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.2128575999858016, |
| "min": -1.0000000521540642, |
| "max": 1.2128575999858016, |
| "count": 17 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 71.55859839916229, |
| "min": -30.331601656973362, |
| "max": 71.55859839916229, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.08625079860409596, |
| "min": 0.08625079860409596, |
| "max": 7.604195029474795, |
| "count": 17 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 5.088797117641661, |
| "min": 5.088797117641661, |
| "max": 121.66712047159672, |
| "count": 17 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 17 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 17 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1777211945", |
| "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", |
| "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training_1 --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": "1777213070" |
| }, |
| "total": 1124.9908681449997, |
| "count": 1, |
| "self": 0.5347418509995805, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01991339899996092, |
| "count": 1, |
| "self": 0.01991339899996092 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1124.4362128950002, |
| "count": 1, |
| "self": 0.7297435449704608, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.2816635670001233, |
| "count": 1, |
| "self": 2.2816635670001233 |
| }, |
| "TrainerController.advance": { |
| "total": 1121.41658331203, |
| "count": 33155, |
| "self": 0.7267180860485496, |
| "children": { |
| "env_step": { |
| "total": 769.5420282249852, |
| "count": 33155, |
| "self": 688.3621011839036, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 80.7302132740092, |
| "count": 33155, |
| "self": 2.528849327090029, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 78.20136394691917, |
| "count": 32767, |
| "self": 78.20136394691917 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.4497137670723532, |
| "count": 33155, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1121.2244427579517, |
| "count": 33155, |
| "is_parallel": true, |
| "self": 494.2237498019972, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0018577669998194324, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005981829995107546, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012595840003086778, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012595840003086778 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05001835900020524, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000593998000567808, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005207499998505227, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005207499998505227 |
| }, |
| "communicator.exchange": { |
| "total": 0.047078810000130034, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.047078810000130034 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018248009996568726, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003805699998338241, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014442309998230485, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014442309998230485 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 627.0006929559545, |
| "count": 33154, |
| "is_parallel": true, |
| "self": 17.481418120063154, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 12.174977224905433, |
| "count": 33154, |
| "is_parallel": true, |
| "self": 12.174977224905433 |
| }, |
| "communicator.exchange": { |
| "total": 539.7229246840079, |
| "count": 33154, |
| "is_parallel": true, |
| "self": 539.7229246840079 |
| }, |
| "steps_from_proto": { |
| "total": 57.62137292697798, |
| "count": 33154, |
| "is_parallel": true, |
| "self": 11.982562276967656, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 45.63881065001033, |
| "count": 265232, |
| "is_parallel": true, |
| "self": 45.63881065001033 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 351.14783700099633, |
| "count": 33155, |
| "self": 1.3211543039465141, |
| "children": { |
| "process_trajectory": { |
| "total": 66.08043701904444, |
| "count": 33155, |
| "self": 65.9015423650444, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.17889465400003246, |
| "count": 1, |
| "self": 0.17889465400003246 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 283.7462456780054, |
| "count": 227, |
| "self": 158.3459020819846, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 125.40034359602078, |
| "count": 11931, |
| "self": 125.40034359602078 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.7249994925805368e-06, |
| "count": 1, |
| "self": 1.7249994925805368e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.00822074600000633, |
| "count": 1, |
| "self": 0.00014616600037697935, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.00807457999962935, |
| "count": 1, |
| "self": 0.00807457999962935 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
