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.
Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require optimization of an objective that is non-linear in cumulative rewards for which dynami…
This paper reports applications of Difference of Convex functions (DC) programming to Learning from Demonstrations (LfD) and Reinforcement Learning (RL) with expert data. This is made possible because the norm of the Optimal Bellman Residual (OBR), which is at the heart of many RL and LfD algorithms, is DC. Improvement…
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize…
Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play t…
Paper tackles goal-directed generation of discrete structures using conditional generative models.
problem Challenges in generating structured discrete data, especially for problems like program synthesis and materials design.
method Investigates conditional generative models to directly model the distribution of discrete structures given properties of interest. Introduces a novel approach to optimize a reinforcement learning objective.
result Improvements over maximum likelihood estimation and other baselines in generating molecules and identifying short python expressions.
The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both estimation and control into one model. However, real-world applications of reinforc…
Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images o…
This paper optimizes sampling policies for Bayesian optimization to improve exploration and exploitation.
problem Improving the balance between exploration and exploitation in Bayesian optimization.
method Developed efficient methods to estimate and optimize non-myopic acquisition functions using rollout policies and stochastic gradient optimization.
result Efficient optimization of sampling policies leads to better performance in Bayesian optimization.
We study the problem of stopping a Brownian motion at a given distribution ν while optimizing a reward function that depends on the (possibly randomized) stopping time and the Brownian motion. Our first result establishes that the set T(ν) of stopping times embedding ν is weakly dense in the set $\mathc…
We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…
Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level detail…
We present a fully nonparametric method to estimate the value function, via simulation, in the context of expected infinite-horizon discounted rewards for Markov chains. Estimating such value functions plays an important role in approximate dynamic programming and applied probability in general. We incorporate "soft in…
The paper identifies all ε-optimal arms in a bandit problem with Gaussian rewards.
problem Identifying all ε-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards.
method The paper provides two lower bounds and a Track-and-Stop strategy to solve the problem, with an efficient numerical method to solve the convex max-min program.
result The Track-and-Stop strategy has asymptotically optimal average sample complexity in the regime of low risk.
We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents polic…
We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of variables that is linear in the number of states. To address this issue, recent …