5 papers
Universal Sample-Based Embeddings of Higher-Order Objects
Radovan Haluška, Christopher Solinas, Nathan R. Sturtevant +2
Neural networks operate naturally on finite-dimensional vectors, yet many problems require reasoning about higher-order objects such as distributions, functions, and graphs. Such o…
Belief Embedding Tree Search
Christopher Solinas, Radovan Haluška, Martin Schmid +3
Beliefs in a Partially Observable Markov Decision Process (POMDP) are posterior distributions over the hidden state given the agent's history of actions and observations. They summ…
Neural Bayesian Filtering
Christopher Solinas, Radovan Haluska, David Sychrovsky +6
Sequential estimation under partial observability requires tracking beliefs that may be high-dimensional, multimodal, and non-Gaussian. Classical Bayesian filters generalize zero-s…
Meta-Learning in Self-Play Regret Minimization
David Sychrovský, Martin Schmid, Michal Šustr +1
Regret minimization is a general approach to online optimization which plays a crucial role in many algorithms for approximating Nash equilibria in two-player zero-sum games. The l…
Approximating Nash Equilibria in General-Sum Games via Meta-Learning
David Sychrovský, Christopher Solinas, Revan MacQueen +4
Nash equilibrium is perhaps the best-known solution concept in game theory. Such a solution assigns a strategy to each player which offers no incentive to unilaterally deviate. Whi…