Mark Rowland

activity

20152024

most citedMastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning

153 citations · 860 across the 45 of their papers we have counts for

collaborators

Showing 2024Show all

2 papers · 1 filter

cs.LG2024

Off-policy Distributional Q( $λ$ ): Distributional RL without Importance Sampling

Yunhao Tang, Mark Rowland, Rémi Munos +2

We introduce off-policy distributional Q( $λ$ ), a new addition to the family of off-policy distributional evaluation algorithms. Off-policy distributional Q( $λ$ ) does not apply impo…

cs.LG2024★ 1 cited

Generalized Preference Optimization: A Unified Approach to Offline Alignment

Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng +7

Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices. We propose generalized preferenc…

Off-policy Distributional Q(λ): Distributional RL without Importance Sampling

Generalized Preference Optimization: A Unified Approach to Offline Alignment

Off-policy Distributional Q( $λ$ ): Distributional RL without Importance Sampling