{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8599633574485779, "min": 0.8599633574485779, "max": 0.8599633574485779, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 15520.619140625, "min": 15520.619140625, "max": 15520.619140625, "count": 1 }, "Pyramids.Step.mean": { "value": 89984.0, "min": 89984.0, "max": 89984.0, "count": 1 }, "Pyramids.Step.sum": { "value": 89984.0, "min": 89984.0, "max": 89984.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10127768665552139, "min": -0.10127768665552139, "max": -0.10127768665552139, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.381431579589844, "min": -14.381431579589844, "max": -14.381431579589844, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17203567922115326, "min": 0.17203567922115326, "max": 0.17203567922115326, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 24.429065704345703, "min": 24.429065704345703, "max": 24.429065704345703, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06334216419012613, "min": 0.06334216419012613, "max": 0.06334216419012613, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2533686567605045, "min": 0.2533686567605045, "max": 0.2533686567605045, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00018090784972408638, "min": 0.00018090784972408638, "max": 0.00018090784972408638, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0007236313988963455, "min": 0.0007236313988963455, "max": 0.0007236313988963455, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.2992082335999994e-05, "min": 5.2992082335999994e-05, "max": 5.2992082335999994e-05, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00021196832934399998, "min": 0.00021196832934399998, "max": 0.00021196832934399998, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11766400000000002, "min": 0.11766400000000002, "max": 0.11766400000000002, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.4706560000000001, "min": 0.4706560000000001, "max": 0.4706560000000001, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.0017746336000000003, "min": 0.0017746336000000003, "max": 0.0017746336000000003, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.007098534400000001, "min": 0.007098534400000001, "max": 0.007098534400000001, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10569269955158234, "min": 0.10569269955158234, "max": 0.10569269955158234, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.42277079820632935, "min": 0.42277079820632935, "max": 0.42277079820632935, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1135634500533342, "min": 1.1135634500533342, "max": 1.1135634500533342, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 17.817015200853348, "min": 17.817015200853348, "max": 17.817015200853348, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729485907", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729485971" }, "total": 64.39221033100011, "count": 1, "self": 0.846474371000113, "children": { "run_training.setup": { "total": 0.05253644699996585, "count": 1, "self": 0.05253644699996585 }, "TrainerController.start_learning": { "total": 63.493199513000036, "count": 1, "self": 0.03421665900100379, "children": { "TrainerController._reset_env": { "total": 1.8634459940001307, "count": 1, "self": 1.8634459940001307 }, "TrainerController.advance": { "total": 61.414933784998766, "count": 1768, "self": 0.03682404100254644, "children": { "env_step": { "total": 41.88220661299761, "count": 1768, "self": 37.45286929799977, "children": { "SubprocessEnvManager._take_step": { "total": 4.406817632000866, "count": 1768, "self": 0.12678290500116418, "children": { "TorchPolicy.evaluate": { "total": 4.280034726999702, "count": 1768, "self": 4.280034726999702 } } }, "workers": { "total": 0.022519682996971824, "count": 1768, "self": 0.0, "children": { "worker_root": { "total": 62.942129577001424, "count": 1768, "is_parallel": true, "self": 28.6303863380017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019833699998343945, "count": 1, "is_parallel": true, "self": 0.0006671329997516295, "children": { "_process_rank_one_or_two_observation": { "total": 0.001316237000082765, "count": 8, "is_parallel": true, "self": 0.001316237000082765 } } }, "UnityEnvironment.step": { "total": 0.05535886300003767, "count": 1, "is_parallel": true, "self": 0.0006598769996344345, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004526940001596813, "count": 1, "is_parallel": true, "self": 0.0004526940001596813 }, "communicator.exchange": { "total": 0.052558122000164076, "count": 1, "is_parallel": true, "self": 0.052558122000164076 }, "steps_from_proto": { "total": 0.0016881700000794808, "count": 1, "is_parallel": true, "self": 0.00034941400053867255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013387559995408083, "count": 8, "is_parallel": true, "self": 0.0013387559995408083 } } } } } } }, "UnityEnvironment.step": { "total": 34.311743238999725, "count": 1767, "is_parallel": true, "self": 0.9216294459997698, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6539582459990925, "count": 1767, "is_parallel": true, "self": 0.6539582459990925 }, "communicator.exchange": { "total": 30.09883404499851, "count": 1767, "is_parallel": true, "self": 30.09883404499851 }, "steps_from_proto": { "total": 2.637321502002351, "count": 1767, "is_parallel": true, "self": 0.5235672419960338, "children": { "_process_rank_one_or_two_observation": { "total": 2.113754260006317, "count": 14136, "is_parallel": true, "self": 2.113754260006317 } } } } } } } } } } }, "trainer_advance": { "total": 19.495903130998613, "count": 1768, "self": 0.048150782994298424, "children": { "process_trajectory": { "total": 3.7887640780043057, "count": 1768, "self": 3.7887640780043057 }, "_update_policy": { "total": 15.658988270000009, "count": 7, "self": 8.391535989999056, "children": { "TorchPPOOptimizer.update": { "total": 7.267452280000953, "count": 615, "self": 7.267452280000953 } } } } } } }, "trainer_threads": { "total": 1.9060000795434462e-06, "count": 1, "self": 1.9060000795434462e-06 }, "TrainerController._save_models": { "total": 0.18060116900005596, "count": 1, "self": 0.0040906670001277234, "children": { "RLTrainer._checkpoint": { "total": 0.17651050199992824, "count": 1, "self": 0.17651050199992824 } } } } } } }