135 search results - page 11 / 27 » Bounded Parameter Markov Decision Processes |
Publication
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained duri...
NIPS
2008
13 years 9 months ago
2008
Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces. Decisions are based on a Particle Filter for estimating the bel...
ML
2002
ACM
13 years 7 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
ISAAC
2010
Springer
13 years 5 months ago
2010
Springer
Howard's policy iteration algorithm is one of the most widely used algorithms for finding optimal policies for controlling Markov Decision Processes (MDPs). When applied to we...
AAAI
2006
13 years 9 months ago
2006
Partially observable Markov decision processes (POMDPs) are an intuitive and general way to model sequential decision making problems under uncertainty. Unfortunately, even approx...