arXiv research

Introduces Conditional Action Trees to simplify RL action spaces.

Efficient algorithm for reinforcement learning in large state-action spaces with adaptive discretization.

TPGR uses a tree structure to improve efficiency and effectiveness in large-scale interactive recommendation.

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the many real-world tasks involving large numbers of discrete actions for which curren…

Adaptive discretization improves model-based RL in large spaces.

Stochastic Q-learning tackles large action spaces with reduced computation.

Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.

New RL algorithm tackles complex discrete action spaces.

A new framework handles hybrid action spaces in reinforcement learning.

It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequ…

ZoomRL learns efficient strategies for large state-action spaces using a metric.

For a discrete metric space (or more generally a large scale space) $X$ and an action of a group $G$ on $X$ by coarse equivalences, we define a type of coarse quotient space $X_G$, which agrees up to coarse equivalence with the orbit space $X/G$ when $G$ is finite. We then restrict our attention to what we call coarsel…

POTEC tackles off-policy learning in large action spaces, improving effectiveness.

New estimator improves off-policy evaluation for large action spaces.

AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.

Discrete groups act properly on 3-space, solving Milnor's question.

New algorithm tracks changes in infinite action space rewards.

We use the combinatorial harmonic map theory to study the isometric actions of discrete groups on Hadamard spaces. Given a finitely generated group acting by automorphisms, properly discontinuously and cofinitely on a simplicial complex and its isometric action on a Hadamard space, we formulate criterions for the actio…

In this article, we sketch an algorithm that extends the Q-learning algorithms to the continuous action space domain. Our method is based on the discretization of the action space. Despite the commonly used discretization methods, our method does not increase the discretized problem dimensionality exponentially. We wil…

Direct policy gradients optimize policies in discrete action spaces using sampling.

New spaces found without certain actions, using special subgroups.

The paper studies fundamental groups of orbit configuration spaces and proves their torsion-freeness.

This paper improves MADDPG's performance in discrete grid-world scenarios.

Discretizes diffusion processes on covering spaces.

We discuss how the global geometry and topology of manifolds depend on different group actions of their fundamental groups, and in particular, how properties of a non-trivial compact 4-dimensional cobordism $M$ whose interior has a complete hyperbolic structure depend on properties of the variety of discrete representa…

Let G be a group and let M be a CAT(0) proper metric space (e.g. a simply connected complete Riemannian manifold of non-positive sectional curvature or a locally finite tree). Isometric actions of G on M are (by definition) points in the space R := Hom(G, Isom(M)) with the compact open topology. Sample theorems: 1. The…

Local-to-global principle for Morse actions on symmetric spaces.

Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.

Proposes hybrid reinforcement learning for both discrete and continuous control problems.

Develops a statistical learning framework for personalized asset allocation.

Stochastic domains often involve risk-averse decision makers. While recent work has focused on how to model risk in Markov decision processes using risk measures, it has not addressed the problem of solving large risk-averse formulations. In this paper, we propose and analyze a new method for solving large risk-averse …

Let Gamma_0 be a discrete group. For a pair (j,rho) of representations of Gamma_0 into PO(n,1)=Isom(H^n) with j geometrically finite, we study the set of (j,rho)-equivariant Lipschitz maps from the real hyperbolic space H^n to itself that have minimal Lipschitz constant. Our main result is the existence of a geodesic l…

New algorithms tackle multi-agent problems with hybrid action spaces.

Hybrid RL method optimizes trading by balancing continuous and discrete actions.

Discretizes diffusions and harmonic functions on covering spaces.

Study shows how certain spaces can be mapped to R^n with specific properties.

Study finite group actions on aspherical manifolds, proving rigidity and symmetry bounds.

Study finite group actions on manifolds with non-zero degree maps to nilmanifolds.

DNAF accelerates DQL for efficient resource allocation in network slicing.

New Soft Actor-Critic for discrete actions.

Investigates offline RL in factorisable action spaces, overcoming overestimation bias.

Morse theory on complexes for CAT(0) groups.

We survey some results and questions about free actions of infinite groups on products of spheres and euclidean spaces, and give some new co-compact examples.

This is the second of two papers in which we prove that a cell model of the moduli space of curves with marked points and tangent vectors at the marked points acts on the Hochschild co--chains of a Frobenius algebra. We also prove that a there is dg--PROP action of a version of Sullivan Chord diagrams which acts on the…

The paper tackles multi-player information asymmetry bandits in metric spaces.

Let G/H be a strongly regular homogeneous space such that H is a Lie group of inner type. We show that G/H admits a proper action of a discrete non-virtually abelian subgroup of G if and only if G/H admits a proper action of a subgroup L of G locally isomorphic to SL(2,R). We classify all such spaces.

We study the geometry and dynamics of discrete infinite covolume subgroups of higher rank semisimple Lie groups. We introduce and prove the equivalence of several conditions, capturing "rank one behavior'' of discrete subgroups of higher rank Lie groups. They are direct generalizations of rank one equivalents to convex…

We extend the notion of Novikov-Shubin invariant for free G-CW-complexes of finite type to spaces with arbitrary G-actions and prove some statements about their positivity. In particular we apply this to classifying spaces of discrete groups.