Markov Models
FACMAC: Factored Multi-Agent Centralised Policy Gradients Bei Peng University of Liverpool T abish Rashid University of Oxford Christian A. Schroeder de Witt
However, unlike QMIX, there are no inherent constraints on factoring the critic. We thus also employ a nonmonotonic factorisation and empirically demonstrate that its increased representational capacity allows it to solve some tasks that cannot be solved with monolithic, or monotonically factored critics.
Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
Multi-agent control is a central theme in the Cyber-Physical Systems (CPS) . However, current control methods either receive non-Markovian states due to insufficient sensing and decentralized design, or suffer from poor convergence.
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play.
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play.
Information is Power: Intrinsic Control via Information Capture
Figure 1: The agent uses a latent state space model to represent beliefs about the world, including dynamic objects like the goat. The blue window represents the agent's field-of-view, which defines the extent of the
A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP
As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available.