arXiv research

The paper introduces MDP homomorphic networks for faster reinforcement learning.

This work uses action equivariance to learn structured latent spaces for reinforcement learning.

This paper optimizes MDP policies for efficient state aggregation.

Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is b…

Characterizes a general range decreasing group homomorphism.

We extend certain homomorphisms defined on the higher Torelli subgroups of the mapping class group to crossed homomorphisms defined on the entire mapping class group. In particular, for every $k\geq 2$, we construct a crossed homomorphism $ε_k$ which extends Morita's homomorphism $\tilde τ_k$ to the entire mapping clas…

Adaptive reduction scheme approximates optimal policy in regularized MDPs.

We study Exo-MDPs to reduce sample complexity in reinforcement learning.

In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyz…

Two crossing homomorphisms on braid groups are shown to be equivalent.

The study classifies homomorphisms from mapping class groups using finite subgroups.

Paper establishes new lower bounds for MDPs with changing transition kernels.

Study of Chebyshev-Frobenius homomorphism in 3-manifold skein modules.

We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present …

Graph homomorphism numbers embed graphs for classification.

New conditions for weighted composition operators in group homomorphisms.

New method approximates POMDPs with PB-MDPs, providing error bounds and practical algorithms.

We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimen…

Study homomorphisms from groups to 3-manifold fundamental groups.

Optimizes learning policies in MDPs with weakly communicating structure.

New homomorphism from Khovanov homology for knot concordance.

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across…

New method removes oracle and reduces memory usage for robust MDPs.

DeepAveragers solves offline RL by solving derived MDPs from static data.

New RL method learns to skip states in linearly $q^π$-realizable MDPs, simplifying to linear MDPs.

We introduce the notion of tight homomorphism into a locally compact group with nonvanishing bounded cohomology and study these homomorphisms in detail when the target is a Lie group of Hermitian type. Tight homomorphisms between Lie groups of Hermitian type give rise to tight totally geodesic maps of Hermitian symmetr…

A chord index homomorphism for knots in thickened surfaces is constructed.

Study classifies biharmonic and harmonic homomorphisms between specific Lie groups.

Study on Euler class and flux homomorphisms for non-orientable surfaces.

We examine functorial and homotopy properties of the exotic characteristic homomorphism in the category of Lie algebroids which was lastly obtained by the authors in [4]. This homomorphism depends on a triple (A,B,$\nabla$) where B $\subset$ A are regular Lie algebroids, both over the same regular foliated manifold (M,…

Optimizes learning policies in average-reward MDPs with improved sample complexity.

We define an infinite family of linearly independent, integer-valued smooth concordance homomorphisms. Our homomorphisms are explicitly computable and rely on local equivalence classes of knot Floer complexes over the ring $\mathbb{F}[U, V]/(UV=0)$. We compare our invariants to other concordance homomorphisms coming fr…

A new homomorphism connects group actions on circles to Euler classes.

We extend each higher Johnson homomorphism to a crossed homomorphism from the automorphism group of a finite-rank free group to a finite-rank abelian group. We also extend each Morita homomorphism to a crossed homomorphism from the mapping class group of once-bounded surface to a finite-rank abelian group. This improve…

We consider bundle homomorphisms between tangent distributions and vector bundles of the same rank. We study the conditions for fundamental singularities when the bundle homomorphism is induced from a Morin map. When the tangent distribution is the contact structure, we characterize singularities of the bundle homomorp…

We propose an approach to study non-Abelian Iwasawa theory, using the idea of Johnson homomorphisms in low dimensional topology. We introduce arithmetic analogues of Johnson homomorphisms/maps, called the p-Johnson homomorphisms/maps, associated to the Zassenhaus filtration of a pro-p Galois group over a Z_p-extension …

Efficiently plans large MDPs with weak function approximations.

We solve POMDPs by approximating them as finite-state MDPs.

Satellite operations with winding number ≠ 1 are not homomorphisms.

Reward suffices for convex MDPs, expanding RL to new problems.

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this study, we propose a novel simulator-based method to approximately solve a CMDP pr…

The paper addresses statistical estimation in MDPs with confounders using instrumental variables.

Homomorphism from braid groups to Steinberg groups defined.

Johnson and Livingston have characterized peripheral structures in homomorphs of knot groups. We extend their approach to the case of links. The main result is an algebraic characterization of all possible peripheral structures in certain homomorphic images of link groups.

Study on regret minimization in deterministic MDPs.

Improved regret bound for MNL MDPs with variance-aware approach.

The paper studies symmetries in quandles and their relative versions.

New method tackles MDPs by learning normalized representations efficiently.