102 search results - page 14 / 21 » MDPs with Non-Deterministic Policies |
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
ICML
2001
IEEE
14 years 8 months ago
2001
IEEE
This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
AAAI
2010
13 years 9 months ago
2010
Trial-based approaches offer an efficient way to solve singleagent MDPs and POMDPs. These approaches allow agents to focus their computations on regions of the environment they en...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
We consider the problem of multi-task reinforcement learning, where the agent needs to solve a sequence of Markov Decision Processes (MDPs) chosen randomly from a fixed but unknow...