{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.5034246444702148, "min": 1.5034246444702148, "max": 1.5034246444702148, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 45607.890625, "min": 45607.890625, "max": 45607.890625, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.18031790852546692, "min": -0.18031790852546692, "max": -0.18031790852546692, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -42.73534393310547, "min": -42.73534393310547, "max": -42.73534393310547, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.19152510166168213, "min": 0.19152510166168213, "max": 0.19152510166168213, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 45.391448974609375, "min": 45.391448974609375, "max": 45.391448974609375, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0716974082898367, "min": 0.0716974082898367, "max": 0.0716974082898367, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5018818580288569, "min": 0.5018818580288569, "max": 0.5018818580288569, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007697324133381511, "min": 0.007697324133381511, "max": 0.007697324133381511, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.053881268933670574, "min": 0.053881268933670574, "max": 0.053881268933670574, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013835433959619045, "min": 0.00013835433959619045, "max": 0.00013835433959619045, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009684803771733332, "min": 0.0009684803771733332, "max": 0.0009684803771733332, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1461180952380953, "min": 0.1461180952380953, "max": 0.1461180952380953, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.022826666666667, "min": 1.022826666666667, "max": 1.022826666666667, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.004617197714285715, "min": 0.004617197714285715, "max": 0.004617197714285715, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.032320384, "min": 0.032320384, "max": 0.032320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.424130916595459, "min": 0.424130916595459, "max": 0.424130916595459, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.968916416168213, "min": 2.968916416168213, "max": 2.968916416168213, "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": 8.953767689876258, "min": 8.953767689876258, "max": 8.953767689876258, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 143.26028303802013, "min": 143.26028303802013, "max": 143.26028303802013, "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": "1748427203", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748427261" }, "total": 58.233437822999804, "count": 1, "self": 0.4362452879995544, "children": { "run_training.setup": { "total": 0.021715381000831258, "count": 1, "self": 0.021715381000831258 }, "TrainerController.start_learning": { "total": 57.77547715399942, "count": 1, "self": 0.0352893760191364, "children": { "TrainerController._reset_env": { "total": 2.2427645660000053, "count": 1, "self": 2.2427645660000053 }, "TrainerController.advance": { "total": 55.37960114498037, "count": 1896, "self": 0.03992810796262347, "children": { "env_step": { "total": 35.950463134007805, "count": 1896, "self": 31.172813437055993, "children": { "SubprocessEnvManager._take_step": { "total": 4.756973386970458, "count": 1896, "self": 0.13903502697849035, "children": { "TorchPolicy.evaluate": { "total": 4.6179383599919674, "count": 1896, "self": 4.6179383599919674 } } }, "workers": { "total": 0.02067630998135428, "count": 1896, "self": 0.0, "children": { "worker_root": { "total": 57.35537149798529, "count": 1896, "is_parallel": true, "self": 29.314976506003404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020529370003714575, "count": 1, "is_parallel": true, "self": 0.0006752650006092153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013776719997622422, "count": 8, "is_parallel": true, "self": 0.0013776719997622422 } } }, "UnityEnvironment.step": { "total": 0.0467068179996204, "count": 1, "is_parallel": true, "self": 0.0005192240005271742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004764280001836596, "count": 1, "is_parallel": true, "self": 0.0004764280001836596 }, "communicator.exchange": { "total": 0.04412000999946031, "count": 1, "is_parallel": true, "self": 0.04412000999946031 }, "steps_from_proto": { "total": 0.0015911559994492563, "count": 1, "is_parallel": true, "self": 0.00033996299953287235, "children": { "_process_rank_one_or_two_observation": { "total": 0.001251192999916384, "count": 8, "is_parallel": true, "self": 0.001251192999916384 } } } } } } }, "UnityEnvironment.step": { "total": 28.040394991981884, "count": 1895, "is_parallel": true, "self": 0.9406066899873622, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6961545339918302, "count": 1895, "is_parallel": true, "self": 0.6961545339918302 }, "communicator.exchange": { "total": 23.528452249011025, "count": 1895, "is_parallel": true, "self": 23.528452249011025 }, "steps_from_proto": { "total": 2.875181518991667, "count": 1895, "is_parallel": true, "self": 0.5931898639464634, "children": { "_process_rank_one_or_two_observation": { "total": 2.2819916550452035, "count": 15160, "is_parallel": true, "self": 2.2819916550452035 } } } } } } } } } } }, "trainer_advance": { "total": 19.38920990300994, "count": 1896, "self": 0.04552560200863809, "children": { "process_trajectory": { "total": 3.461035165002613, "count": 1896, "self": 3.461035165002613 }, "_update_policy": { "total": 15.88264913599869, "count": 7, "self": 8.70107598699633, "children": { "TorchPPOOptimizer.update": { "total": 7.181573149002361, "count": 663, "self": 7.181573149002361 } } } } } } }, "trainer_threads": { "total": 1.0559997463133186e-06, "count": 1, "self": 1.0559997463133186e-06 }, "TrainerController._save_models": { "total": 0.11782101100016007, "count": 1, "self": 0.0015779099994688295, "children": { "RLTrainer._checkpoint": { "total": 0.11624310100069124, "count": 1, "self": 0.11624310100069124 } } } } } } }