5 papers
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
Chulabhaya Wijesundara, Andrea Baisero, Zhongheng Li +3
Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, allowing agents to learn from j…
Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning
Andrea Baisero, Rupali Bhati, Shuo Liu +2
Value function decomposition methods for cooperative multi-agent reinforcement learning compose joint values from individual per-agent utilities, and train them using a joint objec…
On Stateful Value Factorization in Multi-Agent Reinforcement Learning
Enrico Marchesini, Andrea Baisero, Rupali Bhati +1
Value factorization is a popular paradigm for designing scalable multi-agent reinforcement learning algorithms. However, current factorization methods make choices without full jus…
On Centralized Critics in Multi-Agent Reinforcement Learning
Xueguang Lyu, Andrea Baisero, Yuchen Xiao +2
Centralized Training for Decentralized Execution where agents are trained offline in a centralized fashion and execute online in a decentralized manner, has become a popular approa…
Equivariant Reinforcement Learning under Partial Observability
Hai Nguyen, Andrea Baisero, David Klee +3
Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable d…