arXiv research

SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is available. With a Lipschitz continuous policy improvement operator that is smooth eno…

SS-SARSA tackles recovering bandits by treating rounds as states.

The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its…

Implicit Q-learning and SARSA adjust step-sizes automatically, improving stability and performance.

Swift-Sarsa combines TD learning with Sarsa to control tasks robustly.

FedSARSA converges with heterogeneous agents, achieving linear speed-up.

We present a method for Temporal Difference (TD) learning that addresses several challenges faced by robots learning to navigate in a marine environment. For improved data efficiency, our method reduces TD updates to Gaussian Process regression. To make predictions amenable to online settings, we introduce a sparse app…

Temporal-difference (TD) learning is an important field in reinforcement learning. Sarsa and Q-Learning are among the most used TD algorithms. The Q($σ$) algorithm (Sutton and Barto (2017)) unifies both. This paper extends the Q($σ$) algorithm to an online multi-step algorithm Q($σ, λ$) using eligibility traces and int…

Off-policy learning is powerful for reinforcement learning. However, the high variance of off-policy evaluation is a critical challenge, which causes off-policy learning falls into an uncontrolled instability. In this paper, for reducing the variance, we introduce control variate technique to $\mathtt{Expected}$ $\math…

Study evaluates reinforcement learning for trading diverse stocks, finds Q-learning outperforms.

Multi-step methods such as Retrace($λ$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations rarely include enough samples to draw statistically significant conclusions about thei…

Recently, a new multi-step temporal learning algorithm, called $Q(σ)$, unifies $n$-step Tree-Backup (when $σ=0$) and $n$-step Sarsa (when $σ=1$) by introducing a sampling parameter $σ$. However, similar to other multi-step temporal-difference learning algorithms, $Q(σ)$ needs much memory consumption and computation tim…

Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree bac…

Paper proposes a new RL approach combining IL and RL methods to improve decision-making.

We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best…

Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q$(σ,λ)$ is the first approach unifies them with eligibility trace through the sampling degree $σ$. However, it is limited to the tabular case, for large-scale …

In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning methods are very promising but rely on epsilon-greedy exploration, thus subjecting…

A softmax operator applied to a set of values acts somewhat like the maximization function and somewhat like an average. In sequential decision making, softmax is often used in settings where it is necessary to maximize utility but also to hedge against problems that arise from putting all of one's weight behind a sing…

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the gradient, instead of relying only on the action in the sampled trajectory. We es…

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the model-free Reinforcement Learning setting, where we do not have access to the mod…

New algorithms for n-player games using a player-centered approach.

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-proce…

Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been…

As sensor networks for health monitoring become more prevalent, so will the need to control their usage and consumption of energy. This paper presents a method which leverages the algorithm's performance and energy consumption. By utilising Reinforcement Learning (RL) techniques, we provide an adaptive framework, which…

TDprop uses Jacobi preconditioning to improve adaptive optimizers in Deep RL.

Transformers can implement reinforcement learning algorithms from data without updates.

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory…

Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberat…

Tabular Q-learning outperforms advanced RL methods in monetary policy.

Continuous-time Q-learning theory developed for reinforcement learning.

When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a significant effect on an agent's performance, however, and determining a suitable approximation arch…