Computer Science – Artificial Intelligence
Scientific paper
2010-11-19
Computer Science
Artificial Intelligence
Scientific paper
We investigate projection methods, for evaluating a linear approximation of the value function of a policy in a Markov Decision Process context. We consider two popular approaches, the one-step Temporal Difference fix-point computation (TD(0)) and the Bellman Residual (BR) minimization. We describe examples, where each method outperforms the other. We highlight a simple relation between the objective function they minimize, and show that while BR enjoys a performance guarantee, TD(0) does not in general. We then propose a unified view in terms of oblique projections of the Bellman equation, which substantially simplifies and extends the characterization of (schoknecht,2002) and the recent analysis of (Yu & Bertsekas, 2008). Eventually, we describe some simulations that suggest that if the TD(0) solution is usually slightly better than the BR solution, its inherent numerical instability makes it very bad in some cases, and thus worse on average.
No associations
LandOfFree
Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-116916