FIELD NOTES TOPIC
experiment results
2 notes, newest first.
MemHarness: Memory Is Reconstructed, Not Replayed
Researchers have developed MemHarness, a framework to improve large language model agents by enabling them to adapt and reconstruct past experiences based on the current context, instead of simply replaying stored…
LaGO: Latent Action Guidance for Online Reinforcement Learning
The paper 'LaGO: Latent Action Guidance for Online Reinforcement Learning' proposes a new framework called LaGO. This framework uses a pre-trained language model (LLM) as a guide to help with online policy optimization…
