Filter agent RL credit assignment methods by supervision, learned value critic, granularity and evaluation setting, wit…
Filter agent RL credit assignment methods by supervision, learned value critic, granularity and evaluation setting, with original section evidence and BibTeX. Compare memory, observation and terminal benchmarks; retrieve paper passages and inspect ShellOps tasks.
agentic-rl
cli
free
Others in the same category, ranked by how often they are opened.
