1 citations · 2 across the 9 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Partial Action Replacement: Tackling Distribution Shift in Offline MARL
Yue Jin, Giovanni Montana
Offline multi-agent reinforcement learning (MARL) is severely hampered by the challenge of evaluating out-of-distribution (OOD) joint actions. Our core finding is that when the beh…
cs.LG2025
Evaluation-Time Policy Switching for Offline Reinforcement Learning
Natinael Solomon Neggatu, Jeremie Houssineau, Giovanni Montana
Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed…