Results 271 to 280 of about 7,093,982 (312)

Fitted policy search

2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2011
In this paper we address the combination of batch reinforcement-learning (BRL) techniques with direct policy search (DPS) algorithms in the context of robot learning. Batch value-based algorithms (such as fitted Q-iteration) have been proved to outperform online ones in many complex applications, but they share the same difficulties in solving problems
MIGLIAVACCA, MARTINO, A. Pecorino, PIROTTA, MATTEO, RESTELLI, MARCELLO, BONARINI, ANDREA   +4 more
openaire   +1 more source

Covariant Policy Search

2018
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geometric methods. This leads us to propose a natural metric on controller parameterization that results from considering the manifold of probability distributions over paths ...
J. Andrew Bagnell, Jeff G. Schneider
openaire   +2 more sources

Policy Search by Dynamic Programming

2018
We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to visit each state), then we can derive a policy search algorithm that terminates in a finite number of steps, and for which we can provide non-trivial performance guarantees.
J. Andrew Bagnell, Sham M. Kakade, Andrew Y. Ng, Jeff G. Schneider   +3 more
openaire   +2 more sources

Privatisation: A Policy in Search of a Rationale

The Economic Journal, 1986
Privatisation is a term which is used to cover several distinct, and possibly alternative, means of changing the relationships between the government and the private sector. Among the most important of these are denationalisation (the sale of publicly owned assets), deregulation (the introduction of competition into statutory monopolies) and ...
Kay, J A, Thompson, D J
openaire   +1 more source

Search for optimal sailing policy

European Journal of Operational Research, 2017
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Shaul P. Ladany, Ofer Levi
openaire   +2 more sources

Relative Entropy Policy Search

Proceedings of the AAAI Conference on Artificial Intelligence, 2010
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients, many of these problems may be addressed by constraining the
Peters, J., Mülling, K., Altun, Y.
openaire   +2 more sources

Searching for a Rationale for Search Design Policy

SSRN Electronic Journal, 2016
This paper concurs in the debate about search design and the antitrust action that the European Commission is bringing against Google in Europe. Faced with the radical changes that the internet has brought to markets and social life, antitrust principles and paradigm of analysis are still be applied as if we were dealing in a world of brick-and-mortar ...
Massimiliano Granieri, Valeria Falce
openaire   +1 more source

The search for coherence in reproductive policy

Journal of Legal Medicine, 1996
Children of Choice: Freedom and the New Reproductive Technologies, by John A. Robertson (Princeton University Press, Princeton, New Jersey, 1994), 277 pages, $29.95. Human Reproduction, Emerging Technologies, and Conflicting Rights, by Robert Blank & Janna C.
openaire   +2 more sources

Policy Search for Motor Primitives.

Künstliche Intell., 2009
Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space.
Peters, J., Kober, J.
openaire   +2 more sources