Âóùöòòð Óó Öøø¬ Blockin

By Milos Hauskre. 2000

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Shaping Belief States with Generative Environment Models for RL (2019, background): “A key concept in POMDPs is the notion of a belief-state, which can be defined as the sufficient statistics of future states [6, 7, 8].”
Sidekick agents for sequential planning problems (2013, background): “V'QMDP is a tighter lower bound for V* than VIML [29].”
Reinforcement Learning with Limited Reinforcement : Using Bayes Risk for Active Learning in POMDPs Finale (2012, background): “5An interesting area for future work might be to compute tight er risk values using different underlying approximations, such as the fast informed bound [30].”
Reinforcement Learning: A Tutorial Survey and Recent Advances (2009, unknown): “Several other papers (Gordon, 1995; Hauskrecht, 2000; Dayan, 1992; Tsitsiklis and van Roy, 1996) discuss the issue of function approximation.”
Online Planning Algorithms for POMDPs (2008, methodology): “We present various combinations of online algorithms with various existing offline algorithms, such as QMDP (Littman, Cassandra, & Kaelbling, 1995), FIB (Hauskrecht, 2000), Blind (Hauskrecht, 2000; Smith & Simmons, 2005) and PBVI (Pineau et al., 2003).”
A Framework for Sequential Planning in Multi-Agent Settings (2005, methodology): “Background: Partially Observable Markov Decision Processes A partially observable Markov decision process (POMDP) (Monahan, 1982; Hausktecht, 1997; Kaelbling et al., 1998; Boutilier et al., 1999; Hauskrecht, 2000) of an agent i is defined as POMDPi = 〈S,Ai, Ti,Ωi, Oi, Ri〉 (1) where: S is a set of po”
Neural belief states for partially observed domains (2018, background): “Alternatively, an optimal policy can depend on a statistic bt of the history ht, as long as bt is sufficient for predicting future observations; in a POMDP, bt is known as a belief state [1, 2, 3].”
Policy-Gradient Algorithms for Partially Observable Markov Decision Processes (2003, methodology): “The longterm reward of optimal MDP methods upper bounds the reward that can be obtained after introducing partial observability [Hauskrecht, 2000].”
Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution (2011, background): “The agent’s policy is stochastic, given by the softmax of the lookahead state-action value function QLA (Hauskrecht, 2000): P (a|b,x,y) ∝ exp(βQLA(b,x,y,a)).”