MP-DQN
MP-DQN copied to clipboard
Source code for the dissertation: "Multi-Pass Deep Q-Networks for Reinforcement Learning with Parameterised Action Spaces"
Hi! For my Master's thesis, I'm looking to use the MP-DQN algorithm in order to solve a problem. However, I'd like to use a dueling network to speed up convergence....
``` /home/tj/anaconda3/envs/p-dqn/bin/python3 /snap/pycharm-professional/171/helpers/pydev/pydevd.py --multiproc --qt-support=auto --client 127.0.0.1 --port 40821 --file /home/tj/PycharmProjects/MP-DQN/run_soccer_qpamdp.py pydev debugger: process 7349 is connecting Connected to pydev debugger (build 192.7142.56) /home/tj/anaconda3/envs/p-dqn/lib/python3.6/site-packages/hfo_py/bin/HFO Starting server with command: /home/tj/anaconda3/envs/p-dqn/lib/python3.6/site-packages/hfo_py/bin/HFO --headless...
Hello. I have a few questions. 1, What the effect of variable "shrink" in the class "SarsaLambdaAgent"? And Can I use other basis instead, like the polynomial basis? 2, Why...
I have trained a model for "soccer pdqn", and I want to finetune a new work based on the trained model, what should I do?