{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.7546901106834412, "min": 0.7546901106834412, "max": 1.418938398361206, "count": 233 }, "Worm.Policy.Entropy.sum": { "value": 22640.703125, "min": 22640.703125, "max": 42568.15234375, "count": 233 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 233 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 233 }, "Worm.Step.mean": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Step.sum": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 238.57986450195312, "min": -0.030264511704444885, "max": 238.7449493408203, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 7157.39599609375, "min": -0.8776708245277405, "max": 7162.3486328125, "count": 233 }, "Worm.Environment.CumulativeReward.mean": { "value": 1188.4943888346354, "min": 0.17140958830714226, "max": 1188.6684448242188, "count": 233 }, "Worm.Environment.CumulativeReward.sum": { "value": 35654.83166503906, "min": 5.142287649214268, "max": 35660.05334472656, "count": 233 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1188.4943888346354, "min": 0.17140958830714226, "max": 1188.6684448242188, "count": 233 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 35654.83166503906, "min": 5.142287649214268, "max": 35660.05334472656, "count": 233 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01411332649392231, "min": 0.01047790824668482, "max": 0.0235713456256365, "count": 232 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01411332649392231, "min": 0.01047790824668482, "max": 0.0235713456256365, "count": 232 }, "Worm.Losses.ValueLoss.mean": { "value": 11.896761213030134, "min": 0.0010334085063299252, "max": 13.696317945207868, "count": 232 }, "Worm.Losses.ValueLoss.sum": { "value": 11.896761213030134, "min": 0.0010334085063299252, "max": 13.696317945207868, "count": 232 }, "Worm.Policy.LearningRate.mean": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.LearningRate.sum": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.Epsilon.mean": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Epsilon.sum": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Beta.mean": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 }, "Worm.Policy.Beta.sum": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683739604", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/home/mark/rl_course/.unit5_venv/bin/mlagents-learn ./ml-agents/config/ppo/Worm.yaml --env=./ml-agents/training-envs-executables/linux/Worm/Worm --run-id=Worm1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683750109" }, "total": 10504.193586319685, "count": 1, "self": 0.3231488047167659, "children": { "run_training.setup": { "total": 0.013392854947596788, "count": 1, "self": 0.013392854947596788 }, "TrainerController.start_learning": { "total": 10503.85704466002, "count": 1, "self": 13.384338697884232, "children": { "TrainerController._reset_env": { "total": 5.288313401862979, "count": 1, "self": 5.288313401862979 }, "TrainerController.advance": { "total": 10485.048619326204, "count": 701000, "self": 13.016889019403607, "children": { "env_step": { "total": 8093.429603974801, "count": 701000, "self": 7228.569016146474, "children": { "SubprocessEnvManager._take_step": { "total": 855.4780502999201, "count": 701000, "self": 45.95606778562069, "children": { "TorchPolicy.evaluate": { "total": 809.5219825142995, "count": 701000, "self": 809.5219825142995 } } }, "workers": { "total": 9.382537528406829, "count": 701000, "self": 0.0, "children": { "worker_root": { "total": 10480.880464751739, "count": 701000, "is_parallel": true, "self": 4168.93715487374, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022225920110940933, "count": 1, "is_parallel": true, "self": 0.0005126679316163063, "children": { "_process_rank_one_or_two_observation": { "total": 0.001709924079477787, "count": 2, "is_parallel": true, "self": 0.001709924079477787 } } }, "UnityEnvironment.step": { "total": 0.028827323112636805, "count": 1, "is_parallel": true, "self": 0.0005137305706739426, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008109067566692829, "count": 1, "is_parallel": true, "self": 0.0008109067566692829 }, "communicator.exchange": { "total": 0.026349851861596107, "count": 1, "is_parallel": true, "self": 0.026349851861596107 }, "steps_from_proto": { "total": 0.0011528339236974716, "count": 1, "is_parallel": true, "self": 0.00031482381746172905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008380101062357426, "count": 2, "is_parallel": true, "self": 0.0008380101062357426 } } } } } } }, "UnityEnvironment.step": { "total": 6311.943309877999, "count": 700999, "is_parallel": true, "self": 229.04008141485974, "children": { "UnityEnvironment._generate_step_input": { "total": 382.5745876613073, "count": 700999, "is_parallel": true, "self": 382.5745876613073 }, "communicator.exchange": { "total": 5163.548799792305, "count": 700999, "is_parallel": true, "self": 5163.548799792305 }, "steps_from_proto": { "total": 536.7798410095274, "count": 700999, "is_parallel": true, "self": 143.95231797220185, "children": { "_process_rank_one_or_two_observation": { "total": 392.8275230373256, "count": 1401998, "is_parallel": true, "self": 392.8275230373256 } } } } } } } } } } }, "trainer_advance": { "total": 2378.602126332, "count": 701000, "self": 17.068648553453386, "children": { "process_trajectory": { "total": 389.50852839881554, "count": 701000, "self": 387.6618690909818, "children": { "RLTrainer._checkpoint": { "total": 1.846659307833761, "count": 14, "self": 1.846659307833761 } } }, "_update_policy": { "total": 1972.024949379731, "count": 233, "self": 1759.5650872197002, "children": { "TorchPPOOptimizer.update": { "total": 212.45986216003075, "count": 9786, "self": 212.45986216003075 } } } } } } }, "trainer_threads": { "total": 1.2759119272232056e-06, "count": 1, "self": 1.2759119272232056e-06 }, "TrainerController._save_models": { "total": 0.13577195815742016, "count": 1, "self": 0.0016271830536425114, "children": { "RLTrainer._checkpoint": { "total": 0.13414477510377765, "count": 1, "self": 0.13414477510377765 } } } } } } }