Shanchao Yang

infinite loop: after run this code "findLegallyConnectedComponents "

2

I wonder that when the function""findLegallyConnectedComponents " is planning to return,but it stuck into returning .Could someone help me with that?

Real recurrent policy supported

2

**Are you requesting a feature or an implementation?** To handle the partial MDP task, the recurrent policy is currently quite popular. We need to add a lstm layer after the...

Possible bug of the calculation precision

5

Hello, Lucas First, thanks for your code. Now I'm using your ppo algorithm for my project. But I found a possible issue of the number precision, which may cause the...

Should we mask out the entropy

1

Hey, Thanks for your work. There is one point I am not quite sure. Since the action probs for all the heads except for the first catgorical one are masked...

Hi, Thanks for your excellent development of deepagents. I am curious about how to use CodeAct agent as subagent. For example, the react-based coding agent is given as: https://github.com/langchain-ai/langgraph-codeact ....