SHITIANYU

icon indicating a website link https://shitianyu-hue.github.io/

icon company University of Toronto icon location Toronto, Canada icon location Ph.D. student @ University of Toronto Reinforcement learning

Results 37 comments of SHITIANYU

rl-agents compatible with continuous action spaces

Thanks for your reply and valuable suggestions!

rl-agents compatible with continuous action spaces

Hello, I tried the stable baselines with DDPG algorithm, but I found the agent can't learn a reasonable policy. The agent just drives around in a circle. here is the...

Could you give any instruction about how to run the code

could you show me your error

Could you give any instruction about how to run the code

hi you can first try IDM

Pygame error

I run the test.py file, but it occurs this error.

Pygame error

Thanks for your reply, I will try it in the monitor👍

I can't seem to run the test.py.

I have the same error too

Update wave_attenuation.py

Sorry, i am not quite familiar with:pydocstyle --convention numpy, but i am sure this can run successfully.

singleagent_merge training fails

i also fail to train single agent merge, multiagent merge fails too....QAQ

minicity environment for multiagent training

ok, thanks, i found it works. Could you release the code in this paper?https://sites.google.com/view/iccps-policy-transfer