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 14 of 14 for “"Q-functions"”.

  1. Symmetric functions, shifted tableaux, and a class of distinct Schur Q-functions

    The Schur Q-functions form a basis of the algebra Ω of symmetric functions generated by the odd-degree power sum basis pd, and have ramifications in the projective representations of the symmetric group. So, as with ordinary Schur functions, it is relevant to consider the equality of skew Schur …

    colostate Repository record for Symmetric functions, shifted tableaux, and a class of distinct Schur Q-functions (opens in a new tab)

  2. The wisdom of the crowd: reliable deep reinforcement learning through ensembles of Q-functions

    Reinforcement learning agents learn by exploring the environment and then exploiting what they have learned. This frees the human trainers from having to know the preferred action or intrinsic value of each encountered state. The cost of this freedom is reinforcement learning can feel too slow and …

    colostate Repository record for The wisdom of the crowd: reliable deep reinforcement learning through ensembles of Q-functions (opens in a new tab)

  3. Design and performance analysis of quadratic-form receivers for fading channels

    … the first-order and the generalized Marcum Q-functions arise very often in the performance analysis of QFRs, we also derive some new representations and bounds for these Q-functions by using a new geometric approach, and apply the results obtained to the performance analysis of QFRs over …

    nus Repository record for Design and performance analysis of quadratic-form receivers for fading channels (opens in a new tab) Download file for Design and performance analysis of quadratic-form receivers for fading channels (opens in a new tab)

  4. Adaptive Interventions Treatment Modelling and Regimen Optimization Using Sequential Multiple Assignment Randomized Trials (Smart) and Q-Learning

    … or in other words approximate the function, Q-functions. Then the approximated functions of the model should be evaluated and after the evaluation they should be further tested for applying the treatment rule to future patients. Thus, in this thesis first the dataset obtained from Sanford …

    sdstate Repository record for Adaptive Interventions Treatment Modelling and Regimen Optimization Using Sequential Multiple Assignment Randomized Trials (Smart) and Q-Learning (opens in a new tab)

  5. Equivariant Giambelli Formulae for Grassmannians

    … coincide with the factorial Schur S, P, and Q functions. We define factorial theta polynomials, and conjecture that these represent the Schubert classes in the equivariant cohomology of non-maximal symplectic Grassmannians. We prove that the factorial theta polynomials satisfy the equivariant …

    maryland Repository record for Equivariant Giambelli Formulae for Grassmannians (opens in a new tab)

  6. Autonomous Driving: A Multi-Objective Deep Reinforcement Learning Approach

    … structure of a task. Specifically, factored Q functions learned on the factored state space can be used as features to the original Q function to speed up learning. 3. Inclusion of history-dependent policies enables an intuitive exact algorithm for multi-objective reinforcement learning with …

    waterloo Repository record for Autonomous Driving: A Multi-Objective Deep Reinforcement Learning Approach (opens in a new tab)

  7. Bi-fractional transforms in phase space

    … respect to the density operator gives the Wigner functions (displaced parity operator) and Weyl functions (displacement operator). The generalisation of the parity-displacement operator relationship considered here is called the bi-fractional displacement operator, O(α, β; θα, θβ). Additionally, …

    bradford Repository record for Bi-fractional transforms in phase space (opens in a new tab)

  8. Theta Maps for Combinatorial Hopf Algebras

    … generalize marked shifted tableaux and Schur's Q functions. Nyman shows that it is a the sum of permutations with the same peak set. Aguiar, Bergeron and Sottile show that the peak algebra is the odd Hopf sub-algebra of quasi symmetric functions using their theory of combinatorial Hopf algebras. …

    york Repository record for Theta Maps for Combinatorial Hopf Algebras (opens in a new tab)

  9. On the role of time horizons in reinforcement learning

    … of the long-term action-value: (1) Truncated Q-functions, representing the first n steps of a rollout corresponding to the target-policy of the full action-value and (2) Shifted Q-functions, representing the expected return after this truncated rollout. This decomposition leading to the …

    freiburg-diss Repository record for On the role of time horizons in reinforcement learning (opens in a new tab)

  10. Reinforcement Learning-Based Mobile Underwater Acoustic Communications

    … adaptive system, the receiver sends truncated q-functions to the transmitter, which then performs mapping selection for the individual sub-carriers. Simulations demonstrate the advantages of the proposed adaptive system, achieving higher data rates and lower feedback costs. The second effort …

    alabama Repository record for Reinforcement Learning-Based Mobile Underwater Acoustic Communications (opens in a new tab)

  11. Classical and quantum phase-space measures for information flow and non-markovianity

    … by the Kolmogorov distance between Glauber P-functions and Husimi Q-functions and we will prove the existence of some optimal ordering such that the Kolmogorov distance between the respectively ordered quasi-distributions equals the trace distance. The Kolmogorov dis- tance represents in this …

    freiburg-diss Repository record for Classical and quantum phase-space measures for information flow and non-markovianity (opens in a new tab)

  12. Fine-Grained Analysis of Select Statistical Problems

    … by leveraging latent structures resulting in Q functions with a low-rank matrix representation. We introduce an offline policy evaluation algorithm that utilizes this low-rank characteristic to estimate values for state-action pairs that are not covered. Remarkably, our approach operates without …

    cornell Repository record for Fine-Grained Analysis of Select Statistical Problems (opens in a new tab)

  13. Risk-Aware Safety in Multi-Agent Systems - Online CVaR Q-Learning, Q-Function–Multiplier Decoupling, and the Centralised Scaling Bottleneck

    … one; we decouple the reward and cost Q-functions, running them as separate recursions that recombine only at action selection; and we source the multiplier signal from a rolling buffer of return samples rather than from the cost Q-function itself. We then stress-test the resulting …

    chalmers Repository record for Risk-Aware Safety in Multi-Agent Systems - Online CVaR Q-Learning, Q-Function–Multiplier Decoupling, and the Centralised Scaling Bottleneck (opens in a new tab)

  14. Βελτιστοποίηση και αξιολόγηση της επίδοσης ασύρματων ψηφιακών συστημάτων επικοινωνίας με πολλαπλές κεραίες εκπομπής και λήψης

    … standard Nuttall, and the normalized Nuttall Q-functions through the definition of a new function, called the generalized incomplete gamma ratio. The offered theoretical results can be efficiently applied to the information-theoretic analysis of MIMO systems, among others.

    greece Repository record for Βελτιστοποίηση και αξιολόγηση της επίδοσης ασύρματων ψηφιακών συστημάτων επικοινωνίας με πολλαπλές κεραίες εκπομπής και λήψης (opens in a new tab)