{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32153427600860596, "min": 0.32153427600860596, "max": 1.439545750617981, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9656.3173828125, "min": 9656.3173828125, "max": 43670.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5534831881523132, "min": -0.1114935427904129, "max": 0.5643879175186157, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.20787048339844, "min": -26.869943618774414, "max": 160.28616333007812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019495638087391853, "min": 0.009569132700562477, "max": 0.2746480107307434, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.361300468444824, "min": 2.602804183959961, "max": 65.0915756225586, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06698466799326609, "min": 0.06432440363942019, "max": 0.074208014857332, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9377853519057252, "min": 0.4975411588367578, "max": 1.063690218880462, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015524686607690357, "min": 0.0002747564665469168, "max": 0.016534531303997423, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21734561250766501, "min": 0.002472808198922251, "max": 0.23894182990382734, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.610754605971427e-06, "min": 7.610754605971427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010655056448359997, "min": 0.00010655056448359997, "max": 0.0030213977928675003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253688571428572, "min": 0.10253688571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355164, "min": 1.3691136000000002, "max": 2.4373203, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026343488285714286, "min": 0.00026343488285714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368808836, "min": 0.00368808836, "max": 0.10074253675, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0116520244628191, "min": 0.0116520244628191, "max": 0.46599823236465454, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1631283462047577, "min": 0.1631283462047577, "max": 3.2619876861572266, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 348.33734939759034, "min": 328.9587628865979, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28912.0, "min": 15984.0, "max": 32676.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5826618855907804, "min": -1.0000000521540642, "max": 1.606572891663139, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.94359838962555, "min": -32.000001668930054, "max": 154.23099759966135, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5826618855907804, "min": -1.0000000521540642, "max": 1.606572891663139, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.94359838962555, "min": -32.000001668930054, "max": 154.23099759966135, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04159526883603619, "min": 0.04038628669832178, "max": 9.212507023476064, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.49400258222704, "min": 3.385106544010341, "max": 147.40011237561703, "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": "1712324509", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712326614" }, "total": 2104.987759824, "count": 1, "self": 0.5579477300002509, "children": { "run_training.setup": { "total": 0.054430416000002424, "count": 1, "self": 0.054430416000002424 }, "TrainerController.start_learning": { "total": 2104.375381678, "count": 1, "self": 1.255782363977687, "children": { "TrainerController._reset_env": { "total": 3.1023866029999567, "count": 1, "self": 3.1023866029999567 }, "TrainerController.advance": { "total": 2099.931317097022, "count": 63810, "self": 1.3151403090910208, "children": { "env_step": { "total": 1489.9990878649592, "count": 63810, "self": 1362.9235838460281, "children": { "SubprocessEnvManager._take_step": { "total": 126.27869670294587, "count": 63810, "self": 4.783853580958976, "children": { "TorchPolicy.evaluate": { "total": 121.49484312198689, "count": 62560, "self": 121.49484312198689 } } }, "workers": { "total": 0.7968073159851201, "count": 63810, "self": 0.0, "children": { "worker_root": { "total": 2099.2741756799746, "count": 63810, "is_parallel": true, "self": 852.7249502519817, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005151312000009511, "count": 1, "is_parallel": true, "self": 0.0036709660000155964, "children": { "_process_rank_one_or_two_observation": { "total": 0.001480345999993915, "count": 8, "is_parallel": true, "self": 0.001480345999993915 } } }, "UnityEnvironment.step": { "total": 0.04993071100000179, "count": 1, "is_parallel": true, "self": 0.000656163000030574, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004937850000032995, "count": 1, "is_parallel": true, "self": 0.0004937850000032995 }, "communicator.exchange": { "total": 0.0470071389999589, "count": 1, "is_parallel": true, "self": 0.0470071389999589 }, "steps_from_proto": { "total": 0.001773624000009022, "count": 1, "is_parallel": true, "self": 0.0003962619999811068, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013773620000279152, "count": 8, "is_parallel": true, "self": 0.0013773620000279152 } } } } } } }, "UnityEnvironment.step": { "total": 1246.549225427993, "count": 63809, "is_parallel": true, "self": 34.018820331919414, "children": { "UnityEnvironment._generate_step_input": { "total": 24.119135143018923, "count": 63809, "is_parallel": true, "self": 24.119135143018923 }, "communicator.exchange": { "total": 1088.179520958053, "count": 63809, "is_parallel": true, "self": 1088.179520958053 }, "steps_from_proto": { "total": 100.23174899500168, "count": 63809, "is_parallel": true, "self": 20.180032842984758, "children": { "_process_rank_one_or_two_observation": { "total": 80.05171615201692, "count": 510472, "is_parallel": true, "self": 80.05171615201692 } } } } } } } } } } }, "trainer_advance": { "total": 608.6170889229722, "count": 63810, "self": 2.4719350069653956, "children": { "process_trajectory": { "total": 127.15626262500706, "count": 63810, "self": 126.69464205500668, "children": { "RLTrainer._checkpoint": { "total": 0.4616205700003775, "count": 2, "self": 0.4616205700003775 } } }, "_update_policy": { "total": 478.9888912909998, "count": 437, "self": 280.53502759001145, "children": { "TorchPPOOptimizer.update": { "total": 198.45386370098834, "count": 22851, "self": 198.45386370098834 } } } } } } }, "trainer_threads": { "total": 1.1980000635958277e-06, "count": 1, "self": 1.1980000635958277e-06 }, "TrainerController._save_models": { "total": 0.08589441599997372, "count": 1, "self": 0.0013532129996747244, "children": { "RLTrainer._checkpoint": { "total": 0.08454120300029899, "count": 1, "self": 0.08454120300029899 } } } } } } }