We introduce a new convergent variant of Q-learning, called speedy Q-learning (SQL), to address the problem of slow convergence in the standard form of the Q-learning algorithm.

Reinforcement learning models address animal's behavioral adaptation to its changing "external" environment, and are based on the assumption that Pavlovian, habitual and goal-directed responses seek to maximize reward acquisition. Negative-feedback models of homeostatic regulation, on the other hand, are concerned with behavioral adaptation in response to the "internal" state of the animal, and assume that animals' behavioral objective is to minimize deviations of some key physiological variables from their hypothetical setpoints. Building upon the drive-reduction theory of reward, we propose a new analytical framework that integrates learning and regulatory systems, such that the two seemingly unrelated objectives of reward maximization and physiological-stability prove to be identical. The proposed theory shows behavioral adaptation to both internal and external states in a disciplined way. We further show that the proposed framework allows for a unified explanation of some behavioral pattern like motivational sensitivity of different associative learning mechanism, anticipatory responses, interaction among competing motivational systems, and risk aversion.

The problem of selecting the right state-representation in a reinforcement learning problem is considered. Several models (functions mapping past observations to a finite set) of the observations are given, and it is known that for at least one of these models the resulting state dynamics are indeed Markovian. Without knowing neither which of the models is the correct one, nor what are the probabilistic characteristics of the resulting MDP, it is required to obtain as much reward as the optimal policy for the correct model (or for the best of the correct models, if there are several).

Fitted value iteration (FVI) with ordinary least squares regression is known to diverge. We present a new method, "Expansion-Constrained Ordinary Least Squares" (ECOLS), that produces a linear approximation but also guarantees convergence when used with FVI. To ensure convergence, we constrain the least squares regression operator to be a non-expansion in the -norm. We show that the space of function approximators that satisfy this constraint is more rich than the space of "averagers," we prove a minimax property of the ECOLS residual error, and we give an efficient algorithm for computing the coefficients of ECOLS based on constraint generation. We illustrate the algorithmic convergence of FVI with ECOLS in a suite of experiments, and discuss its properties.

In this paper, we consider the problem of policy evaluation for continuousstate systems. We present a non-parametric approach to policy evaluation, which uses kernel density estimation to represent the system. The true form of the value function for this model can be determined, and can be computed using Galerkin's method. Furthermore, we also present a unified view of several well-known policy evaluation methods. In particular, we show that the same Galerkin method can be used to derive Least-Squares Temporal Difference learning, Kernelized Temporal Difference learning, and a discrete-state Dynamic Programming solution, as well as our proposed method. In a numerical evaluation of these algorithms, the proposed approach performed better than the other methods.

The difficulty in inverse reinforcement learning (IRL) arises in choosing the best reward function since there are typically an infinite number of reward functions that yield the given behaviour data as optimal. Using a Bayesian framework, we address this challenge by using the maximum a posteriori (MAP) estimation for the reward function, and show that most of the previous IRL algorithms can be modeled into our framework. We also present a gradient method for the MAP estimation based on the (sub)differentiability of the posterior distribution. We show the effectiveness of our approach by comparing the performance of the proposed method to those of the previous algorithms.

Autonomous parallel-style on-ramp merging in human controlled traffic continues to be an existing issue for autonomous vehicle control. Existing non-learning based solutions for vehicle control rely on rules and optimization primarily. These methods have been seen to present significant challenges. Recent advancements in Deep Reinforcement Learning have shown promise and have received significant academic interest however the available learning based approaches show inadequate attention to other highway vehicles and often rely on inaccurate road traffic assumptions. In addition, the parallel-style case is rarely considered. A novel learning based model for acceleration and lane change decision making that explicitly considers the utility to both the ego vehicle and its surrounding vehicles which may be cooperative or uncooperative to produce behaviour that is socially acceptable is proposed. The novel reward function makes use of Social Value Orientation to weight the vehicle's level of social cooperation and is divided into ego vehicle and surrounding vehicle utility which are weighted according to the model's designated Social Value Orientation. A two-lane highway with an on-ramp divided into a taper-style and parallel-style section is considered. Simulation results indicated the importance of considering surrounding vehicles in reward function design and show that the proposed model matches or surpasses those in literature in terms of collisions while also introducing socially courteous behaviour avoiding near misses and anti-social behaviour through direct consideration of the effect of merging on surrounding vehicles.

A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-player optimizes the sampling distribution against an adversarial max-player that chooses confusing models leading to large regret. The most recent instantiation of this idea is the decision-estimation coefficient (DEC), which was shown to provide nearly tight lower and upper bounds on the worst-case expected regret in structured bandits and reinforcement learning. By re-parametrizing the offset DEC with the confidence radius and solving the corresponding min-max program, we derive an anytime variant of the Estimation-To-Decisions (E2D) algorithm. Importantly, the algorithm optimizes the exploration-exploitation trade-off online instead of via the analysis. Our formulation leads to a practical algorithm for finite model classes and linear feedback models. We further point out connections to the information ratio, decoupling coefficient and PAC-DEC, and numerically evaluate the performance of E2D on simple examples.

Recently there has been a growing interest in industry and academia, regarding the use of wireless chargers to prolong the operational longevity of unmanned aerial vehicles (commonly knowns as drones). In this paper we consider a charger-assisted drone application: a drone is deployed to observe a set points of interest, while a charger can move to recharge the drone's battery. We focus on the route and charging schedule of the drone and the mobile charger, to obtain high observation utility with the shortest possible time, while ensuring the drone remains operational during task execution. Essentially, this proposed drone-charger scheduling problem is a multi-stage decision-making process, in which the drone and the mobile charger act as two agents who cooperate to finish a task. The discrete-continuous hybrid action space of the two agents poses a significant challenge in our problem. To address this issue, we present a hybrid-action deep reinforcement learning framework, called HaDMC, which uses a standard policy learning algorithm to generate latent continuous actions. Motivated by representation learning, we specifically design and train an action decoder. It involves two pipelines to convert the latent continuous actions into original discrete and continuous actions, by which the drone and the charger can directly interact with environment. We embed a mutual learning scheme in model training, emphasizing the collaborative rather than individual actions. We conduct extensive numerical experiments to evaluate HaDMC and compare it with state-of-the-art deep reinforcement learning approaches. The experimental results show the effectiveness and efficiency of our solution.

In image-based robot manipulation tasks with large observation and action spaces, reinforcement learning struggles with low sample efficiency, slow training speed, and uncertain convergence. As an alternative, large pre-trained foundation models have shown promise in robotic manipulation, particularly in zero-shot and few-shot applications. However, using these models directly is unreliable due to limited reasoning capabilities and challenges in understanding physical and spatial contexts. This paper introduces ExploRLLM, a novel approach that leverages the inductive bias of foundation models (e.g. Large Language Models) to guide exploration in reinforcement learning. We also exploit these foundation models to reformulate the action and observation spaces to enhance the training efficiency in reinforcement learning. Our experiments demonstrate that guided exploration enables much quicker convergence than training without it. Additionally, we validate that ExploRLLM outperforms vanilla foundation model baselines and that the policy trained in simulation can be applied in real-world settings without additional training.