Related papers: Generalized Hidden Parameter MDPs Transferable Mod…

Hierarchical model-based reinforcement learning (HMBRL) aims to combine the benefits of better sample efficiency of model based reinforcement learning (MBRL) with the abstraction capability of hierarchical reinforcement learning (HRL) to…

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data…

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

This paper introduces a hybrid algorithm of deep reinforcement learning (RL) and Force-based motion planning (FMP) to solve distributed motion planning problem in dense and dynamic environments. Individually, RL and FMP algorithms each have…

Many problems in sequential decision making and stochastic control often have natural multiscale structure: sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure,…

Latent variable models have accumulated a considerable amount of interest from the industry and academia for their versatility in a wide range of applications. A large amount of effort has been made to develop systems that is able to extend…

Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of…

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However,…

There is considerable interest in designing meta-reinforcement learning (meta-RL) algorithms, which enable autonomous agents to adapt new tasks from small amount of experience. In meta-RL, the specification (such as reward function) of…

Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the…

Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with…

Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified…

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve…

This work shows that value-aware model learning, known for its numerous theoretical benefits, is also practically viable for solving challenging continuous control tasks in prevalent model-based reinforcement learning algorithms. First, we…

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, outside of restrictive…

We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of…

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optimal policy with…

Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential…