|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6534873843193054, |
|
"min": 0.6534873843193054, |
|
"max": 1.5431253910064697, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 19531.431640625, |
|
"min": 19531.431640625, |
|
"max": 50713.2734375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989922.0, |
|
"min": 29952.0, |
|
"max": 989922.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989922.0, |
|
"min": 29952.0, |
|
"max": 989922.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5039507150650024, |
|
"min": -0.12338055670261383, |
|
"max": 0.5929787755012512, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 138.08248901367188, |
|
"min": -29.487953186035156, |
|
"max": 163.66213989257812, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.03150377422571182, |
|
"min": 0.00490775378420949, |
|
"max": 0.4278498888015747, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.632034301757812, |
|
"min": 1.2969324588775635, |
|
"max": 100.11687469482422, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06848002173091645, |
|
"min": 0.06330861079775439, |
|
"max": 0.07399730283015296, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9587203042328304, |
|
"min": 0.4844167022529291, |
|
"max": 1.0347373552549648, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016658629933530296, |
|
"min": 0.0010643052913413462, |
|
"max": 0.016658629933530296, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23322081906942416, |
|
"min": 0.007450137039389423, |
|
"max": 0.23322081906942416, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.547733198407141e-06, |
|
"min": 7.547733198407141e-06, |
|
"max": 0.0002950848016384, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010566826477769997, |
|
"min": 0.00010566826477769997, |
|
"max": 0.0027920981693007004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251587857142859, |
|
"min": 0.10251587857142859, |
|
"max": 0.19836159999999997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4352223000000002, |
|
"min": 1.3684608000000003, |
|
"max": 2.2755587, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002613362692857142, |
|
"min": 0.0002613362692857142, |
|
"max": 0.00983632384, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003658707769999999, |
|
"min": 0.003658707769999999, |
|
"max": 0.09309686007000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013311014510691166, |
|
"min": 0.013190694153308868, |
|
"max": 0.4133564829826355, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18635420501232147, |
|
"min": 0.18466971814632416, |
|
"max": 2.8934953212738037, |
|
"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 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 323.0978260869565, |
|
"min": 323.0978260869565, |
|
"max": 999.0, |
|
"count": 32 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29725.0, |
|
"min": 1685.0, |
|
"max": 62214.0, |
|
"count": 32 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.654105468601971, |
|
"min": -1.0000000521540642, |
|
"max": 1.6611124759539961, |
|
"count": 32 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 150.52359764277935, |
|
"min": -58.27420325577259, |
|
"max": 150.52359764277935, |
|
"count": 32 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.654105468601971, |
|
"min": -1.0000000521540642, |
|
"max": 1.6611124759539961, |
|
"count": 32 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 150.52359764277935, |
|
"min": -58.27420325577259, |
|
"max": 150.52359764277935, |
|
"count": 32 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04542399158142891, |
|
"min": 0.04542399158142891, |
|
"max": 4.694267954826355, |
|
"count": 32 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.133583233910031, |
|
"min": 1.8478424977511168, |
|
"max": 117.35669887065887, |
|
"count": 32 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1682276088", |
|
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", |
|
"command_line_arguments": "/home/byron/miniconda3/envs/torch/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics --torch-device=cuda:0 --num-envs 4 --num-areas 8", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.13.1+cu117", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1682277165" |
|
}, |
|
"total": 1076.351261099, |
|
"count": 1, |
|
"self": 0.4212915969983442, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.023083496998879127, |
|
"count": 1, |
|
"self": 0.023083496998879127 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1075.906886005003, |
|
"count": 1, |
|
"self": 1.1175611507642316, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 12.854328707995592, |
|
"count": 1, |
|
"self": 12.854328707995592 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1061.8692720722465, |
|
"count": 50711, |
|
"self": 1.0072531040204922, |
|
"children": { |
|
"env_step": { |
|
"total": 308.1554301210999, |
|
"count": 50711, |
|
"self": 127.75338604554418, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 179.70773294112587, |
|
"count": 63944, |
|
"self": 3.6913824499060865, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 176.01635049121978, |
|
"count": 62735, |
|
"self": 176.01635049121978 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6943111344298813, |
|
"count": 50711, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4300.106483937736, |
|
"count": 63941, |
|
"is_parallel": true, |
|
"self": 3397.442163723812, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004771393985720351, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.00135901098838076, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0034123829973395914, |
|
"count": 32, |
|
"is_parallel": true, |
|
"self": 0.0034123829973395914 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.12181193399010226, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.000998283998342231, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0016725879977457225, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.0016725879977457225 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.11608262499794364, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.11608262499794364 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.003058436996070668, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.0007625639991601929, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002295872996910475, |
|
"count": 32, |
|
"is_parallel": true, |
|
"self": 0.002295872996910475 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 902.6643202139239, |
|
"count": 63937, |
|
"is_parallel": true, |
|
"self": 16.631254727501073, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.274879490956664, |
|
"count": 63937, |
|
"is_parallel": true, |
|
"self": 12.274879490956664 |
|
}, |
|
"communicator.exchange": { |
|
"total": 828.0996875454002, |
|
"count": 63937, |
|
"is_parallel": true, |
|
"self": 828.0996875454002 |
|
}, |
|
"steps_from_proto": { |
|
"total": 45.65849845006596, |
|
"count": 63937, |
|
"is_parallel": true, |
|
"self": 11.43318056021235, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.22531788985361, |
|
"count": 511496, |
|
"is_parallel": true, |
|
"self": 34.22531788985361 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 752.7065888471261, |
|
"count": 50711, |
|
"self": 2.05000208268757, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 120.992824682442, |
|
"count": 50711, |
|
"self": 120.85008095644298, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14274372599902563, |
|
"count": 2, |
|
"self": 0.14274372599902563 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 629.6637620819965, |
|
"count": 420, |
|
"self": 310.2301196816261, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 319.43364240037045, |
|
"count": 22926, |
|
"self": 319.43364240037045 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 6.999907782301307e-07, |
|
"count": 1, |
|
"self": 6.999907782301307e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.06572337400575634, |
|
"count": 1, |
|
"self": 0.0007505450048483908, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.06497282900090795, |
|
"count": 1, |
|
"self": 0.06497282900090795 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |