We consider actions of Z^k, k \ge 2, by Anosov diffeomorphisms which are uniformly quasiconformal on each coarse Lyapunov distribution. These actions generalize Cartan actions for which coarse Lyapunov distributions are one-dimensional. We show that, under certain non-resonance assumptions on the Lyapunov exponents, a …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “action distribution”
Study of entropy-regularized LQG MFGs with exploratory actions.
problem Optimizing multi-population mean field games with entropy regularization.
method Introduced exploratory actions and derived optimal action distributions.
result Optimal action distributions lead to ε-Nash equilibria in finite-population MFGs.
DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.
problem DRL agents struggle at high decision frequencies, leading to poor performance.
method Proved that DRL agents' action-conditioned return distributions collapse to their policy's return distribution as decision frequency increases. Defined superiority as a probabilistic generalization of advantage for high-frequency value-based RL.
result Proper modeling of superiority distribution improves performance of controllers at high decision frequencies.
GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicingcs.LG
Network slicing is a key technology in 5G communications system. Its purpose is to dynamically and efficiently allocate resources for diversified services with distinct requirements over a common underlying physical infrastructure. Therein, demand-aware resource allocation is of significant importance to network slicin…
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
SDPG algorithm improves sample efficiency and reward in DRL for continuous action spaces.
problem Improving sample efficiency and reward in distributional reinforcement learning for continuous action spaces.
method SDPG algorithm models return distribution using samples via reparameterization technique.
result SDPG shows better sample efficiency and higher reward in OpenAI Gym environments.
Q-Distribution Guided Q-Learning corrects overestimation of uncertain OOD actions in offline RL.
problem Overestimation of Q-values for out-of-distribution actions in offline reinforcement learning.
method QDQ applies a pessimistic adjustment to Q-values in uncertain OOD regions based on a consistency model.
result QDQ improves performance on the D4RL benchmark and achieves significant improvements across many tasks.
Study optimal offline RL with uncertainty sets and distribution shifts.
problem Optimal offline reinforcement learning with limited data.
method Construct uncertainty sets and distribution shifts, solve robust Markov decision process.
result Least conservative estimator for unknown true distribution.
Stochastic games provide a framework for interactions among multiple agents and enable a myriad of applications. In these games, agents decide on actions simultaneously, the state of every agent moves to the next state, and each agent receives a reward. However, finding an equilibrium (if exists) in this game is often …
New RL approach uses future state and action visitation measures for better exploration.
problem Improving exploration in reinforcement learning.
method Intrinsic reward based on future state and action visitation measures, using contraction operators.
result Policies achieve good state-action space coverage and high performance.
Unified reinforcement learning and stochastic processes with action-driven processes.
problem Combining reinforcement learning and stochastic processes for efficient control.
method Action-driven processes, leveraging control-as-inference, and minimizing Kullback-Leibler divergence.
result Action-driven processes unify reinforcement learning and stochastic processes, equivalent to maximum entropy reinforcement learning.
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will …
New method for natural policy gradients converges linearly.
problem Improving natural policy gradient methods for better convergence.
method Fisher-Rao gradient flow applied to state-action distributions.
result Linear convergence rate with geometry-dependent factor.
Let be a Lie foliation on a closed manifold with structural Lie group . Its transverse Lie structure can be considered as a transverse action of on ; i.e., an ``action'' which is defined up to leafwise homotopies. This induces an action of on the reduced leafwis…
We consider a totally nonsymplectic Anosov action of Z^k which is either uniformly quasiconformal or pinched on each coarse Lyapunov distribution. We show that such an action on a torus is C^\infty--conjugate to an action by affine automorphisms. We also obtain similar global rigidity results for actions on an arbitrar…
Method trains neural network for optimal decisions from stochastic simulators.
problem Suboptimal decisions from SBI approximations of posterior distributions.
method Trains neural network on simulated data to predict optimal actions.
result Induces similar cost as true posterior for optimal actions.
Guillemin trace formula adapted for group actions.
problem Distributional trace for proper, cocompact group actions.
method Developing an equivariant version of the distributional trace.
result Equivariant Guillemin trace formula for group actions.
Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present balanced off-policy evaluation (B-OPE), a generic method for estimating weights…
A scheme robust to action erasures improves MAB performance.
problem Learning in multi-arm bandits with erasure channels.
method Proposes a scheme to work on top of any MAB algorithm.
result Worst-case regret is at most a factor of away from no-erasure case.
Hybridizes CEM and gradient descent for efficient model-predictive control.
problem Efficiently planning optimal action sequences in high-dimensional spaces.
method Interleaves Cross-Entropy Method (CEM) and gradient descent steps.
result Faster convergence and avoidance of local optima compared to CEM.
We develop variation formulas on almost-product (e.g. foliated) pseudo-Riemannian manifolds, and we consider variations of metric preserving orthogonality of the distributions. These formulae are applied to Einstein-Hilbert type actions: the total mixed scalar curvature and the total extrinsic scalar curvature of a dis…
Quantum models learn unitary actions on entangled states from product states.
problem Generalization to out-of-distribution data in quantum machine learning.
method Proved out-of-distribution generalization for learning unitary actions.
result Learned unitary actions on entangled states from product states.
Extends distribution algebra concept to Lie groupoids.
problem Distribution algebra on Lie groupoids.
method Construction of convolution C_c(M)/R-bialgebra associated with Lie groupoid adjoint action.
result Extension of Cartier-Gabriel decomposition to Lie groupoids.
The paper introduces a new intrinsic reward method for exploration in reinforcement learning.
problem Improving exploration in reinforcement learning agents.
method Intrinsic rewards proportional to the entropy of future state-action features.
result The new objective leads to improved visitation of features within individual trajectories.
IDAC improves reinforcement learning efficiency by modeling implicit distributions.
problem Improving sample efficiency in reinforcement learning algorithms.
method IDAC uses two DGNs for a distributional critic and a semi-implicit actor to model implicit policy distributions.
result IDAC outperforms state-of-the-art algorithms on OpenAI Gym environments.
Causal Bayesian networks interpret actions as interventions to connect models to real-world outcomes.
problem Connecting causal model predictions to real-world outcomes.
method Formal framework to interpret actions as interventions and prove impossibility results.
result No non-circular interpretation exists that satisfies natural desiderata without violating some.
Identifies latent actions and dynamics from offline data with diverse demonstrators.
problem Recovering latent actions and environment dynamics from action-free trajectories.
method Assumes distinct policies for each demonstrator, identifies latent transitions and policies via matrix factorization.
result Identifies latent transitions and demonstrator policies up to permutation.
On the Equivalence of Optimal Transport Problem and Action Matching with Optimal Vector Fieldsstat.ML
New method AM learns optimal vector fields for entire distribution sequences, matching OT.
problem Optimal Transport (OT) problem in generative modeling.
method Action Matching (AM) method learns optimal vector fields for a sequence of distributions.
result AM method achieves optimal transport by learning vector fields for entire distribution sequences.
Develops a new reinforcement learning framework for complex control problems.
problem Continuous-time extended mean field control with deterministic policies.
method Model-free sensitivity formula, deterministic policy gradient, local value and advantage-rate representations.
result Demonstrates efficiency, stability, and robustness in solving complex control problems.
A New Approach to Personal Income Distributioncond-mat.stat-mech
The results of R^2 dynamical random surface model (2-dimensional quantum gravity with a term) are applied to explain the personal income distribution. A scale invariance exists if there is not the term in the action. The R^2 term provides a typical scale and breaks the scale invariance explicitly in the low…
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…
In this paper we propose a novel framework for decentralized, online learning by many learners. At each moment of time, an instance characterized by a certain context may arrive to each learner; based on the context, the learner can select one of its own actions (which gives a reward and provides information) or reques…
Study of Einstein-Hilbert action on metric-affine spaces with connections.
problem Formulating and solving variational problems for mixed Einstein-Hilbert action.
method Developed variational formulas for extrinsic geometry, derived Euler-Lagrange equations, and characterized critical points.
result Derived new equations analogous to Einstein and Cartan equations, with a new Ricci type tensor.
AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.
problem Difficulty in maximizing over large action spaces in Q-learning.
method Replace expensive maximization over all actions with a maximization over a small subset sampled from a learned proposal distribution.
result AQL outperforms existing methods on continuous control tasks with up to 21 dimensional actions.
State-constrained offline RL expands RL's learning scope.
problem Batch-constrained offline RL limits policies to seen actions.
method Introduces state-constrained offline RL focusing on state distribution.
result Policy can take high-quality out-of-distribution actions.
New extensions for homogeneous distributions on deformations to the normal cone.
problem Extending homogeneous distributions on a specific geometric structure.
method Using the zoom action and Meyer's results on weakly homogeneous distributions.
result All homogeneous extensions of distributions on the DNC are described.
Research examines the distribution of curve components in random multicurves.
problem Distribution of curve components in random multicurves.
method Action of the mapping class group on random multicurves.
result Distribution of curve components analyzed.
We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the actio…
Paper proposes a framework to assess model robustness against adversarial actions.
problem Ensuring model reliability in deployment with varied adversarial conditions.
method Developed a versatile framework for evaluating SVR and relaxed optimization models' robustness.
result Demonstrates model vulnerability without requiring additional test data.
Optimal algorithm for contextual bandits with unknown context distributions.
problem Designing efficient algorithms for contextual bandits with unknown context distributions.
method Cross-learning setting, novel technique for coordinating multiple epochs.
result Nearly tight regret bound of for learning to bid in first-price auctions and sleeping bandits.
Regularizes predictions to encourage beneficial user actions.
problem Learning models affect user actions, but provide no guarantees.
method Introduces look-ahead regularization to anticipate and encourage beneficial actions.
result Effective in promoting beneficial user actions in real and synthetic data.
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
New method learns distribution shifts caused by predictive models in social computing.
problem Learning distribution shifts due to predictive models in social computing.
method Reverse causal model with microfoundation for agents' actions.
result Effective in minimizing performative prediction risk.
We show that the cone associated with a moment map for an action of a torus on a contact compact connected manifold is a convex polyhedral cone and that the moment map has connected fibers provided the dimension of the torus is bigger than 2 and that no orbit is tangent to the contact distribution. This may be consider…
Efficient Empowermentstat.ML
Empowerment quantifies the influence an agent has on its environment. This is formally achieved by the maximum of the expected KL-divergence between the distribution of the successor state conditioned on a specific action and a distribution where the actions are marginalised out. This is a natural candidate for an intr…
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past acti…
We introduce equivariant Liouville forms and Duistermaat-Heckman distributions for Hamiltonian group actions with group valued moment maps. The theory is illustrated by applications to moduli spaces of flat connections on 2-manifolds.
This paper introduces a new market making approach using scaled beta distributions.
problem Inventory management challenges faced by market makers.
method Scaled beta distribution policies for flexible market making actions.
result Flexibility in volume distribution across price intervals improves market making performance.