bugfix: TypeError when adding a batch dimension

[rieuky]

Error Message

File "dqn.py", line 69, in get_action
state = state[np.newaxis, :]
TypeError: tuple indices must be integers or slices, not tuple

Solution

According to the OpenAI Gym source codes, env.reset() seems to return two data (in tuple).
So I added an underscore to successfully unpack the tuple.
I have applied the similar modification to env.step().

Environments

• Ubuntu 20.04
• Python 3.8.10
• OpenAI Gym 0.26.2

[Aprilistic]

Or you can fix this problem by changing
state = env.reset() -> state = env.reset()[0]