• Publications
  • Influence
The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems
TLDR
We study (a simple form of) Q-learning in cooperative multi agent systems under these two perspectives, focusing on the influence of that game structure and exploration strategies on convergence to (optimal and suboptimal) Nash equilibria. Expand
  • 1,093
  • 129
  • PDF
Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
TLDR
This paper presents an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI, including AI planning, decision analysis, operations research, control theory and economics. Expand
  • 1,219
  • 113
  • PDF
CP-nets: A Tool for Representing and Reasoning withConditional Ceteris Paribus Preference Statements
TLDR
We propose a qualitative graphical representation of preferences that reflects conditional dependence and independence of preference statements under a ceteris paribus (all else being equal) interpretation. Expand
  • 666
  • 84
  • PDF
Context-Specific Independence in Bayesian Networks
TLDR
In this paper, we propose a formal notion of context-specific independence (CSI), based on regularities in the conditional probability tables (CPTs) at a node. Expand
  • 740
  • 78
  • PDF
SPUDD: Stochastic Planning using Decision Diagrams
TLDR
We propose and examine a new value iteration algorithm for MDPs that uses algebraic decision diagrams (ADDs) to represent value functions and policies, assuming an ADD input representation of the MDP. Expand
  • 480
  • 66
  • PDF
Planning, Learning and Coordination in Multiagent Decision Processes
TLDR
In this paper, we investigate the extent to which methods from single-agent planning and learning can be applied in multiagent settings. Expand
  • 425
  • 54
  • PDF
Stochastic dynamic programming with factored representations
TLDR
We use dynamic Bayesian networks (with decision trees representing the local families of conditional probability distributions) to represent stochastic actions in an MDP, together with a decision-tree representation of rewards. Expand
  • 417
  • 52
  • PDF
Reasoning With Conditional Ceteris Paribus Preference Statements
TLDR
We propose a graphical representation of preferences that reflects conditional dependence and independence of preference statements under a ceteris paribus (ali else being equal) interpretation. Expand
  • 326
  • 44
  • PDF
Sequential Optimality and Coordination in Multiagent Systems
TLDR
We propose a method for solving sequential multi-agent decision problems by allowing agents to reason explicitly about the specific coordination mechanisms they adopt to resolve coordination problems. Expand
  • 369
  • 43
  • PDF