ElegantRL

ElegantRL copied to clipboard

D:\anconda\envs\pytorch\python.exe C:\Users\user\Desktop\ElegantRL-master\examples\demo_A2C_PPO.py env_args = {'env_name': 'CartPole-v1', 'num_envs': 1, 'max_step': 500, 'state_dim': 4, 'action_dim': 2, 'if_discrete': True} | Arguments Remove cwd: ./CartPole-v1_DiscreteA2C_0 | Evaluator: | `step`: Number of samples, or total...

guest-oo

tensor_action = tensor_action.argmax(dim=1) IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

guest-oo

\demo_A2C_PPO.py env_args = {'env_name': 'CartPole-v1', 'num_envs': 1, 'max_step': 500, 'state_dim': 4, 'action_dim': 2, 'if_discrete': True} | Arguments Remove cwd: ./CartPole-v1_DiscreteA2C_0 | Evaluator: | `step`: Number of samples, or total training...

guest-oo

class mazeenv(gym.Env): def __init__(self): self.action_space = spaces.Discrete(8) self.observation_space = spaces.Box(low=0, high=23, shape=(14,), dtype=np.float32) self.state = None self.seed() self.reset() def seed(self, seed=None): self.np_random, seed = seeding.np_random(seed) return [seed] def step(self, action):...

guest-oo

Pypi的包有问题

2

根据官方文档https://elegantrl.readthedocs.io/en/latest/index.html 使用pip3 install erl --upgrade下载的包版本是0.0.0，无任何内容

Bang0518

DQN

1

请问 我使用helloworld——DQN文件训练完成后 如何保存训练完成的神经网络参数以及在测试中对其进行使用。以及我应该如何设置自己想要的环境而不是gym现成的环境。

guest-oo

Can't run MAPPO because the net.py misses actorMAPPO and criticMAPPO. I see that the bug has been a problem for a long time When the bug can be fix?

chang2727

在net.py中QNetDuel、QNetTwin和QNetTwinDuel网络中都包含一个状态编码部分，但是状态编码部分不是网络的最终输出部分，为什么在状态编码后不加上激活函数呢(if_raw_out=False)？这部分是否可能会对算法性能造成影响呢，因为同样在SAC网络中也有状态编码部分，但是SAC中编码函数后却加入了激活函数。 ``` class QNetDuel(QNetBase): # Dueling DQN def __init__(self, dims: [int], state_dim: int, action_dim: int): super().__init__(state_dim=state_dim, action_dim=action_dim) self.net_state = build_mlp(dims=[state_dim, *dims]) self.net_adv = build_mlp(dims=[dims[-1], 1]) # advantage value self.net_val =...

legao-2

FinRL on Synthetic Indices

4

Firstly, thank you all guys for all the hard work you are putting into this project, its really awesome and user friendly even to newbies like me. I have been...

Tanakablack

a typeError in build_env() function

3

I inherited from gym.Env and created a new class, passing in the additional parameter env_config in the __init__ method of this new class. But when I use train_agent(), the built_env()...

hululu-lzb