NIPS
2001
14 years 25 days ago
2001
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
ESANN
2003
14 years 25 days ago
2003
The resource constraint project scheduling problem (RCPSP) is an NP-hard benchmark problem in scheduling which takes into account the limitation of resources’ availabilities in ...
IJCAI
2001
14 years 25 days ago
2001
We present a dynamic programming approach for the solution of first-order Markov decisions processes. This technique uses an MDP whose dynamics is represented in a variant of the ...
ESANN
2004
14 years 25 days ago
2004
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
AAAI
2006
14 years 26 days ago
2006
Reinforcement learning problems are commonly tackled with temporal difference methods, which attempt to estimate the agent's optimal value function. In most real-world proble...
NIPS
2007
14 years 26 days ago
2007
We combine three threads of research on approximate dynamic programming: sparse random sampling of states, value function and policy approximation using local models, and using lo...
ECAI
2008
Springer
14 years 1 months ago
2008
Springer
In many practical reinforcement learning problems, the state space is too large to permit an exact representation of the value function, much less the time required to compute it. ...
WSC
2007
14 years 1 months ago
2007
Recently developed dual techniques allow us to evaluate a given sub-optimal dynamic portfolio policy by using the policy to construct an upper bound on the optimal value function....
AAAI
2008
14 years 1 months ago
2008
Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...
PRICAI
2000
Springer
14 years 3 months ago
2000
Springer
This paper introduces the even-odd POMDP, an approximation to POMDPs in which the world is assumed to be fully observable every other time step. The even-odd POMDP can be converte...