genrl:一个PyTorch强化学习库，用于可推广和可再现的算法实现，旨在改善RL中的可访问性 （257个子文件） 
make.bat 799B setup.cfg 342B .isort.cfg 200B .coveragerc 446B A2C-CartPole-v0-ep100.db 84KB .gitignore 144B Bandit_demo.ipynb 107KB DQN_demo.ipynb 20KB LICENSE 1KB Makefile 638B README.md 8KB using_vpg.md 5KB CONTRIBUTING.md 5KB Using Custom Policies.md 4KB CODE_OF_CONDUCT.md 3KB GETTING_STARTED.md 3KB Using A2C.md 978B INSTALL.md 636B getting_started.md 27B install.md 19B placeholder 12B placeholder 0B
Categorical_DQN.png 65KB genrl_cropped.png 12KB genrl.png 12KB windows_cpu_build.ps1 236B actor_critic.py 18KB offpolicy.py 10KB sac.py 9KB ppo1.py 9KB values.py 9KB base.py 9KB vector_envs.py 9KB a2c.py 9KB run_cb.py 9KB rollout_storage.py 8KB bandit.py 8KB neural_linpos.py 8KB utils.py 7KB offpolicy.py 7KB base.py 7KB vpg.py 6KB logger.py 6KB utils.py 6KB bayesian.py 6KB neural_noise_sampling.py 6KB classical.py 6KB td3.py 6KB linpos.py 6KB genetic_rl.py 6KB noise.py 5KB ddpg.py 5KB buffers.py 5KB genetic_hyperparam.py 5KB mushroom_bandit.py 5KB bandit.py 5KB base.py 5KB test_data_bandits.py 5KB base_model.py 5KB bootstrap_neural.py 5KB neural_greedy.py 4KB categorical.py 4KB variational.py 4KB gradient.py 4KB atari_preprocessing.py 4KB frame_stack.py 4KB test_dqn.py 4KB transition.py 4KB base.py 4KB test_dqn_cnn.py 4KB statlog_bandit.py 4KB base.py 4KB deep.py 3KB adult_bandit.py 3KB onpolicy.py 3KB covertype_bandit.py 3KB normalize.py 3KB bayesian.py 3KB magic_bandit.py 3KB census_bandit.py 3KB genetic_rl_q_learning.py 3KB conf.py 3KB gym_wrapper.py 3KB onpolicy.py 3KB thompson.py 3KB base.py 3KB neural.py 3KB utils.py 3KB ucb.py 3KB __init__.py 3KB monitor.py 3KB deep_cb.py 3KB epsgreedy.py 3KB setup.py 3KB policies.py 3KB test_utils.py 3KB a2c_cartpole-v0.py 2KB suite.py 2KB models.py 2KB atari_wrappers.py 2KB共 257 条
- 1
- 2
- 3
资源评论
