Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 151 for “"Value Functions"”.

  1. Learning value functions from undirected state-only experience

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-04-12 without embargo terms

    uiuc Repository record for Learning value functions from undirected state-only experience (opens in a new tab)

  2. A Gilmore-Gomory Construction of Integer Programming Value Functions

    … into an integer program (IP) affects the value function and its level sets. We use a Gilmore-Gomory approach to find parametrized IP value functions over a restricted set of variables. We introduce the notion of maximal connected \color{black}subsets of level sets - volumes in which …

    rice Repository record for A Gilmore-Gomory Construction of Integer Programming Value Functions (opens in a new tab)

  3. Real-time scheduling with soft deadlines and cost/value functions

    … that hard ones, and also incorporate the cost or value factors that may be associated with the requests.

    ttu Repository record for Real-time scheduling with soft deadlines and cost/value functions (opens in a new tab)

  4. The sensitivity of optimal value functions in differential inclusion problems

    … by a finite-dimensional vector u, define a Value function V(u) by inducing changes in the problem's optimal value. After Chapter I reviews the calculus of generalized gradients, Chapter II provides a formula for a certain quantitative index of the problem's sensitivity to changes in u: the …

    ubc Repository record for The sensitivity of optimal value functions in differential inclusion problems (opens in a new tab) Download PDF for The sensitivity of optimal value functions in differential inclusion problems (opens in a new tab)

  5. Microcomputer programming package for the assessment of multiattribute value functions

    … attributes. Two separate packages, an additive value function package (DECISION) and a SMART technique package (SMART), are developed based on these algorithms and their validity tested by means of a case study. Both packages are written for use on a standard (256K) IBM PC microcomputer.

    vt Repository record for Microcomputer programming package for the assessment of multiattribute value functions (opens in a new tab)

  6. A Machine Learning Approach for Quadratic and Linear Programming Value Functions

    … in optimization depend on how the optimal value of a linear or quadratic program changes as a function of its right-hand side. For example, in many stochastic programming formulations, the recourse function is explicitly a function of the second-stage right-hand sides. In bilevel programs, …

    rice Repository record for A Machine Learning Approach for Quadratic and Linear Programming Value Functions (opens in a new tab)

  7. Neural Network Approaches for Integer and Linear Program Value Functions: Theory and Applications

    … neural network methods for approximating the value functions of linear and integer programs, which describe how optimal values change with problem's objectives or right-hand side vectors. For linear programs, we propose a structured neural architecture based on a new representation theorem for …

    rice Repository record for Neural Network Approaches for Integer and Linear Program Value Functions: Theory and Applications (opens in a new tab)

  8. Heuristics for Inventory Systems Based on Quadratic Approximation of L-Natural-Convex Value Functions

    … inventory-pricing problem. We approximate the value functions for these models by the class of L-natural-convex quadratic functions, through the technique of linear programming approach to approximate dynamic programming. A series of heuristics are derived based on the quadratic approximation, …

    duke Repository record for Heuristics for Inventory Systems Based on Quadratic Approximation of L-Natural-Convex Value Functions (opens in a new tab)

  9. Adaptive tile coding methods for the generalization of value functions in the RL state space.

    … on the accuracy of the approximated state value functions. Tile coding (Sutton and Barto, 1998), a function approximator method, generalizes the approximated state value functions for the entire state space using a set of tile features (discrete features based on continuous features). The …

    umn Repository record for Adaptive tile coding methods for the generalization of value functions in the RL state space. (opens in a new tab)

  10. Learning to Concurrently Execute Multiple Robotic Tasks – Analysis and Optimization-Based Synthesis

    … of reinforcement learning – each encoded as a value function and executed together as constraints in a pointwise min-norm controller. Applying reinforcement learning to robotic control tasks is an active area of research as it has the potential to generalize to complex tasks. For robots that …

    waterloo Repository record for Learning to Concurrently Execute Multiple Robotic Tasks – Analysis and Optimization-Based Synthesis (opens in a new tab)

  11. Reinforcement Learning Methods for Conic Finance

    … considering nonadditive expectations of risks or value functions. This makes some of the optimization algorithms incompatible with this universe, if not infeasible. It is more evident in the application of Reinforcement Learning algorithms where the underlying principle of TD learning and Bellman …

    maryland Repository record for Reinforcement Learning Methods for Conic Finance (opens in a new tab)

  12. Evaluating sets of multi-attribute alternatives with uncertain preferences

    … model is usually represented with a real value function over the criteria used to evaluate alternatives, and an elicitation procedure is a process of defining such value function. The most preferred alternative will then be the one that maximises the value function. With MAUT models, it is …

    cork Repository record for Evaluating sets of multi-attribute alternatives with uncertain preferences (opens in a new tab)

  13. Optimally Navigating a Piecewise-deterministic World

    … iterative solver to recover the mode-dependent value functions and optimal policies for this problem. The second proposes a model of optimal foraging in a continuous domain while subject to predation. We present numerical experiments to demonstrate the impact of a forager's objective on the …

    cornell Repository record for Optimally Navigating a Piecewise-deterministic World (opens in a new tab)

  14. Feature Selection for Value Function Approximation

    … it to reach its goal. This is quantified with value functions, which evaluate a state and return the sum of rewards the agent can expect to receive from that state. Given a good value function, the agent can choose the actions which maximize this sum of rewards. Value functions are often chosen …

    duke Repository record for Feature Selection for Value Function Approximation (opens in a new tab)

  15. The choice-theoretic characterizations of risk changes and risk attitudes in cumulative prospect theory : a stochastic dominance approach

    … to general reference point and inverse S-shaped value functions. The stochastic dominance conditions identified in this thesis provide an approach for risk preference elicitation in the paradigm of CPT without prior knowledge on the shape of value functions or probability weighting functions, …

    lancaster Download PDF for The choice-theoretic characterizations of risk changes and risk attitudes in cumulative prospect theory : a stochastic dominance approach (opens in a new tab)

  16. Nonlinear Stochastic Systems And Controls: Lotka-Volterra Type Models, Permanence And Extinction, Optimal Harvesting Strategies, And Numerical Methods For Systems Under Partial Observations

    … problems. We construct upper bounds for the value functions, prove the finiteness of the harvesting value, and derive properties of the value functions. Then we construct explicit chattering harvesting strategies and the corresponding lower bounds for the value functions by using the idea of …

    wayne-thes Repository record for Nonlinear Stochastic Systems And Controls: Lotka-Volterra Type Models, Permanence And Extinction, Optimal Harvesting Strategies, And Numerical Methods For Systems Under Partial Observations (opens in a new tab)

  17. Model-based active learning in hierarchical policies

    … elegant ways of decomposing policies and value functions using semi-Markov decision processes. However, there is still a lack of demonstrations in larger nonlinear systems with discrete and continuous variables. To narrow this gap between industrial practices and academic ideas, we address …

    ubc Repository record for Model-based active learning in hierarchical policies (opens in a new tab) Download PDF for Model-based active learning in hierarchical policies (opens in a new tab)

  18. A Projective Method for Measuring Central Illinois Farmers' Reservation Prices for Cash and Intermediate Credit Reserves

    … prices were found by varying parameters of functions reflecting assumed behavior of risk averse decision makers. Such a procedure, however, attenuated validation of the model containing the assumed liquidity value functions. What had been lacking was an empirical method for eliciting these …

    uiuc Repository record for A Projective Method for Measuring Central Illinois Farmers' Reservation Prices for Cash and Intermediate Credit Reserves (opens in a new tab)

  19. Improved worst-case regret bounds for randomized least-squares value iteration

    … work studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm, randomized least-squares value iteration (RLSVI). Our …

    uiuc Repository record for Improved worst-case regret bounds for randomized least-squares value iteration (opens in a new tab)

Page 1 of 8