arXiv research

Optimizes antenna tilt for better QoS in cellular networks.

New reinforcement learning algorithms improve policy optimization with entropy regularization.

Softmax policy gradient achieves global optimality in wide neural networks with entropy regularization.

We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure. In our model, a bipartite graph captures the relationship between actions and a common set of unknowns such that choosing an action reveals observations…

This study analyzes economic policy uncertainty indices using visibility graphs.

PPG separates policy and value function training phases for better reinforcement learning efficiency.

This paper addresses the question of how a previously available control policy $π_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $π_L$ for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the superv…

Paper analyzes neural network complexity for planning problems.

We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the stat…

Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the scope of the chosen parametric probability distribution. We show t…

This paper introduces a new method to evaluate multiple policies simultaneously.

NPMD uses CNNs to optimize policies on low-dimensional manifolds, reducing sample complexity.

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…

RANDPOL uses randomized networks for efficient reinforcement learning in continuous state and action MDPs.

We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal $Q$-func…

While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by hardware and speed constraints. Conventional model compression methods attempt to address this problem by modifying the architecture manually …

Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these li…

Deep neural networks can estimate Q-values efficiently on low-dimensional state-action spaces.

Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor and critic parametrized by neural networks achieve significant empirical success in deep reinforcement learning. However, due to nonconvexity, the global convergence of PPO and TRPO remains less understood, which separates theor…

New approach to understand recurrent policies as FSMs without minimization.

Policy-GNN optimizes GNN aggregation for diverse node iterations.

This work learns exploration policies for unknown distributions using samples and policy gradients.

Paper analyzes NAC with neural networks for efficient policy optimization.

Optimizes wireless network resource management with state-augmented policies.

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample complexity and performance on continuous control problems in exchange for extra com…

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…

This work develops agents to learn generalizable policies for dynamic network environments.

Optimizes insurance pricing by accounting for policyholders' price sensitivity.

Approach to optimize bidding policies offline using reinforcement learning.

Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.

Efficient policy learning from observational data using weighted classification reductions.

New algorithm optimizes interventions under network interference, scaling to large networks.

Solves POMDPs with recurrent neural networks and natural policy gradient.

Develops neural network framework for risk-reward optimization problems.

Improves RL algorithms with two techniques.

Revel tackles safe exploration in RL with verified symbolic policies.

Study how untrained policies explore in RL environments.

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($π$) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. The var…

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely …

Optimal vehicle repositioning policy found for shared mobility services.

Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidati…

This paper identifies drift Lipschitz budget K as key to diffusion policy expressivity and statistical trade-offs.

Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small adversarial perturbations on the input can change the output of the network. Sev…

Graph neural networks optimize radio resource management policies for wireless networks.

We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiab…

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative to previous baseline estimators on tasks with binary action space, inspired by …

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. I…