{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39981216192245483, "min": 0.3934237062931061, "max": 1.415805459022522, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12000.76171875, "min": 11727.173828125, "max": 42949.875, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47213461995124817, "min": -0.08998236060142517, "max": 0.47213461995124817, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.00421142578125, "min": -21.685749053955078, "max": 127.00421142578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013947198167443275, "min": 0.005639095325022936, "max": 0.7673876285552979, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.751796245574951, "min": 1.4661648273468018, "max": 181.87086486816406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06607602317013689, "min": 0.06441689575485027, "max": 0.07608977733144563, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9250643243819164, "min": 0.5326284413201194, "max": 1.061632368825182, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012685747331401908, "min": 0.00015974415388837125, "max": 0.02060795935217349, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17760046263962673, "min": 0.0020766740005488263, "max": 0.1933556058679196, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.509611782542859e-06, "min": 7.509611782542859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010513456495560003, "min": 0.00010513456495560003, "max": 0.003382095272635, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250317142857145, "min": 0.10250317142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350444000000002, "min": 1.3886848, "max": 2.5273650000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600668257142858, "min": 0.0002600668257142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003640935560000001, "min": 0.003640935560000001, "max": 0.11276376350000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013063602149486542, "min": 0.013063602149486542, "max": 0.6733935475349426, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18289043009281158, "min": 0.18289043009281158, "max": 4.713754653930664, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.42857142857144, "min": 404.42857142857144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28310.0, "min": 15984.0, "max": 33467.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5377101155294888, "min": -1.0000000521540642, "max": 1.5377101155294888, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.10199797153473, "min": -30.995801612734795, "max": 109.52339832484722, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5377101155294888, "min": -1.0000000521540642, "max": 1.5377101155294888, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.10199797153473, "min": -30.995801612734795, "max": 109.52339832484722, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05416556147806198, "min": 0.05416556147806198, "max": 14.029539309442043, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7374237419862766, "min": 3.7374237419862766, "max": 224.4726289510727, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1782018132", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/content/mla-env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1782020384" }, "total": 2251.444153767, "count": 1, "self": 0.5320820019996972, "children": { "run_training.setup": { "total": 0.018745389999821782, "count": 1, "self": 0.018745389999821782 }, "TrainerController.start_learning": { "total": 2250.8933263750005, "count": 1, "self": 1.370366650012329, "children": { "TrainerController._reset_env": { "total": 2.1261103269998785, "count": 1, "self": 2.1261103269998785 }, "TrainerController.advance": { "total": 2247.3187540639883, "count": 63595, "self": 1.4177955950499381, "children": { "env_step": { "total": 1614.4767425369819, "count": 63595, "self": 1460.919907630946, "children": { "SubprocessEnvManager._take_step": { "total": 152.7295685970421, "count": 63595, "self": 4.795767912090014, "children": { "TorchPolicy.evaluate": { "total": 147.93380068495208, "count": 62558, "self": 147.93380068495208 } } }, "workers": { "total": 0.8272663089937851, "count": 63595, "self": 0.0, "children": { "worker_root": { "total": 2245.5038703991595, "count": 63595, "is_parallel": true, "self": 900.4123487002844, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001794746999621566, "count": 1, "is_parallel": true, "self": 0.0005548879998968914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012398589997246745, "count": 8, "is_parallel": true, "self": 0.0012398589997246745 } } }, "UnityEnvironment.step": { "total": 0.05108818999997311, "count": 1, "is_parallel": true, "self": 0.0007543070005340269, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005299149997881614, "count": 1, "is_parallel": true, "self": 0.0005299149997881614 }, "communicator.exchange": { "total": 0.04805242299971724, "count": 1, "is_parallel": true, "self": 0.04805242299971724 }, "steps_from_proto": { "total": 0.0017515449999336852, "count": 1, "is_parallel": true, "self": 0.0003668489998744917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013846960000591935, "count": 8, "is_parallel": true, "self": 0.0013846960000591935 } } } } } } }, "UnityEnvironment.step": { "total": 1345.091521698875, "count": 63594, "is_parallel": true, "self": 33.73562890998073, "children": { "UnityEnvironment._generate_step_input": { "total": 23.863708573981967, "count": 63594, "is_parallel": true, "self": 23.863708573981967 }, "communicator.exchange": { "total": 1175.391298154971, "count": 63594, "is_parallel": true, "self": 1175.391298154971 }, "steps_from_proto": { "total": 112.10088605994133, "count": 63594, "is_parallel": true, "self": 23.183467534762713, "children": { "_process_rank_one_or_two_observation": { "total": 88.91741852517862, "count": 508752, "is_parallel": true, "self": 88.91741852517862 } } } } } } } } } } }, "trainer_advance": { "total": 631.4242159319565, "count": 63595, "self": 2.6089071521046208, "children": { "process_trajectory": { "total": 110.7326833688594, "count": 63595, "self": 110.47866564085962, "children": { "RLTrainer._checkpoint": { "total": 0.2540177279997806, "count": 2, "self": 0.2540177279997806 } } }, "_update_policy": { "total": 518.0826254109925, "count": 452, "self": 277.75108658102727, "children": { "TorchPPOOptimizer.update": { "total": 240.3315388299652, "count": 22797, "self": 240.3315388299652 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.07809446600003866, "count": 1, "self": 0.0011726140000973828, "children": { "RLTrainer._checkpoint": { "total": 0.07692185199994128, "count": 1, "self": 0.07692185199994128 } } } } } } }