相关论文: Compositional Automata Embeddings for Goal-Conditi…

Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a…

Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in form of…

We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment. This is achieved by equipping an agent…

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Structure learning of Conditional Random Fields (CRFs) can be cast into an L1-regularized optimization problem. To avoid optimizing over a fully linked model, gain-based or gradient-based feature selection methods start from an empty model…

The measurement of time is central to intelligent behavior. We know that both animals and artificial agents can successfully use temporal dependencies to select actions. In artificial agents, little work has directly addressed (1) which…

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state…

Motivation: Many high-performance DTA models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and can also enable scientists to distill…

Deep reinforcement learning has shown promise in various engineering applications, including vehicular traffic control. The non-stationary nature of traffic, especially in the lane-free environment with more degrees of freedom in vehicle…

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular,…

This article presents a new characterization of controllability and regional controllability of Deterministic Cellular Automata (CA for short). It focuses on analyzing these problems within the framework of control theory, which have been…

We discuss the problem of learning a deterministic finite automaton (DFA) from a confidence oracle. That is, we are given access to an oracle $Q$ with incomplete knowledge of some target language $L$ over an alphabet $\Sigma$; the oracle…

A novel reinforcement learning scheme to synthesize policies for continuous-space Markov decision processes (MDPs) is proposed. This scheme enables one to apply model-free, off-the-shelf reinforcement learning algorithms for finite MDPs to…

Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while data from target domain are not available. In this work, we address learning feature representations which…

Recurrent Neural Networks (RNNs) have achieved tremendous success in processing sequential data, yet understanding and analyzing their behaviours remains a significant challenge. To this end, many efforts have been made to extract finite…

Non-deterministic Finite Automata (NFA) represent regular languages concisely, increasing their appeal for applications such as word recognition. This paper proposes a new approach to generate NFA from an interaction language such as UML…

Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities.…

Bounded rational agents often make decisions by evaluating a finite selection of choices, typically derived from a reference point termed the $`$default policy,' based on previous experience. However, the inherent rigidity of the static…