deep_q_rl

deep_q_rl copied to clipboard

kartikay94

We must choose the network when watching it play using the ale_run_watch.py script

1

Added a sys.argv to `ale_run_watch.py` to choose the network used to play, because this scripts runed the trained network only on the Nature network(`run_nature.py`). If I trained the network with...

yzsatgithub

Hi, I got the "Illegal instruction (core dumped) error" when loading in launcher.py, can you please help? ``` ale.loadROM(full_rom_path, full_core_path) ``` using gdb debugger it shows the following error: ```...

yanpanlau

Implementation of Double DQN

12

I was interested in implementing Double DQN in this source code, so here are my changes. Feel free to pull these into the main codebase. I didn't change much, since...

corywalker

Issue on Input Shape of network

1

For the several networks in the build methods, the width and height may be of the wrong order.

taiharry108

"reward_per_epoch" should be "reward_per_episode" in results.csv

1

davidsj

ale-python-interface is not work

1

wenzezhang

gabriel-komaromy

I don't know if this is a real issue and I don't know any other appropriate place to ask about this, it caused some confusion for me. I assumed it...

redsphinx

Hi, Thanks for reading this post. Currently, I am trying to create my own network for reinforcement learning. To this end, I have adapted the Q network from [Playing Atari...

uniwf2016