Gtjkyu

A-star algorithm for Graph Matching [closed] I am developing an application to mark block diagrams using neo4j together with graph matching. I am marking the diagrams by comparing the teacher's answer graph with the student's answer graph, and I am using graph matching for this. Currently I have implemented detecting of additions, deletions, and substitutions of nodes using Depth-first search in my own way, but I want to understand the other currently existing algorithms, and also know if they are better. Many research papers have mentioned A-star algorithm for graph matching. I find it difficult to understand the pseudo codes in the research papers. I was mostly able to understand what they have described, which is not alot, but I want to understand completely. I would be grateful if someone could explain me how the A-star algorithm for graph matching works, or provide me a link with a better explanation about this algorithm used for error-tolerant graph matching using graph ...

How to train Actor-Critic (A2C) reinforcement learning I am currently been able to train a system using Q-Learning. I will to move it to Actor_Critic (A2C) method. Please don't ask me why for this move, I have to. I am currently borrowing the implementation from https://github.com/higgsfield/RL-Adventure-2/blob/master/1.actor-critic.ipynb The thing is, I am keep getting a success rate of approx ~ 50% (which is basically random behavior). My game is a long episode (50 steps). Should I print out the reward, the value, or what? How should I debug this? Here are some log: simulation episode 2: Success, turn_count =20 loss = tensor(1763.7875) simulation episode 3: Fail, turn_count= 42 loss = tensor(44.6923) simulation episode 4: Fail, turn_count= 42 loss = tensor(173.5872) simulation episode 5: Fail, turn_count= 42 loss = tensor(4034.0889) simulation episode 6: Fail, turn_count= 42 loss = tensor(132.7567) loss = simulation episode 7: Success, turn_count =22 loss = tensor(2099.5344) ...