3 citations · 3 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Reinforcement Learning with Complex (valued) Memories
Sathya Kamesh Bhethanabhotla, Efstratios Gavves, André Biedenkapp
Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring agents to compress temporal information from observations and maintain a me…
cs.LG2026
From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
Christian Gumbsch, Leonardo Barcellona, Lennard Schünemann +7
Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics. Recent work has explored…