This paper presents an approach for accelerated learning of optimal plans for a given task represented using Linear Temporal Logic (LTL) in multi-agent systems. Given a set of options (temporally abstract actions) available to each agent, we convert the task specification into the corresponding Buchi Automaton and proceed with a model-free approach which collects transition samples and constructs a product Semi Markov Decision Process (SMDP) on-the-fly. Value-based Reinforcement Learning algorithms can then be used to synthesize a correct-by-design controller without learning the underlying transition model of the multi-agent system. The exponential sample complexity due to multiple agents is dealt with using a novel reward shaping approach. We test the proposed algorithm in a deterministic gridworld simulation for different tasks and find that the reward shaping results in significant reduction in convergence times. We also infer that using options becomes increasing more relevant as the state and action space increases in multi-agent systems.

Traditional approaches to inference of deterministic finite-state automata (DFA) stem from symbolic AI, including both active learning methods (e.g., Angluin's L* algorithm and its variants) and passive techniques (e.g., Biermann and Feldman's method, RPNI). Meanwhile, sub-symbolic AI, particularly machine learning, offers alternative paradigms for learning from data, such as supervised, unsupervised, and reinforcement learning (RL). This paper investigates the use of Q-learning, a well-known reinforcement learning algorithm, for the passive inference of deterministic finite automata. It builds on the core insight that the learned Q-function, which maps state-action pairs to rewards, can be reinterpreted as the transition function of a DFA over a finite domain. This provides a novel bridge between sub-symbolic learning and symbolic representations. The paper demonstrates how Q-learning can be adapted for automaton inference and provides an evaluation on several examples.

Past research into robotic planning with temporal logic specifications, notably Linear Temporal Logic (LTL), was largely based on singular formulas for individual or groups of robots. But with increasing task complexity, LTL formulas unavoidably grow lengthy, complicating interpretation and specification generation, and straining the computational capacities of the planners. By leveraging the intrinsic structure of tasks, we introduced a hierarchical structure to LTL specifications with requirements on syntax and semantics, and proved that they are more expressive than their flat counterparts. Second, we employ a search-based approach to synthesize plans for a multi-robot system, accomplishing simultaneous task allocation and planning. The search space is approximated by loosely interconnected sub-spaces, with each sub-space corresponding to one LTL specification. The search is predominantly confined to a single sub-space, transitioning to another sub-space under certain conditions, determined by the decomposition of automatons. Moreover, multiple heuristics are formulated to expedite the search significantly. A theoretical analysis concerning completeness and optimality is conducted under mild assumptions. When compared with existing methods on service tasks, our method outperforms in terms of execution times with comparable solution quality. Finally, scalability is evaluated by testing a group of 30 robots and achieving reasonable runtimes.

We examine the assumption that the hidden-state vectors of recurrent neural networks (RNNs) tend to form clusters of semantically similar vectors, which we dub the clustering hypothesis. While this hypothesis has been assumed in the analysis of RNNs in recent years, its validity has not been studied thoroughly on modern neural network architectures. We examine the clustering hypothesis in the context of RNNs that were trained to recognize regular languages. This enables us to draw on perfect ground-truth automata in our evaluation, against which we can compare the RNN's accuracy and the distribution of the hidden-state vectors. We start with examining the (piecewise linear) separability of an RNN's hidden-state vectors into semantically different classes. We continue the analysis by computing clusters over the hidden-state vector space with multiple state-of-the-art unsupervised clustering approaches. We formally analyze the accuracy of computed clustering functions and the validity of the clustering hypothesis by determining whether clusters group semantically similar vectors to the same state in the ground-truth model. Our evaluation supports the validity of the clustering hypothesis in the majority of examined cases. We observed that the hidden-state vectors of well-trained RNNs are separable, and that the unsupervised clustering techniques succeed in finding clusters of similar state vectors.

Motion planning of autonomous agents in partially known environments with incomplete information is a challenging problem, particularly for complex tasks. This paper proposes a model-free reinforcement learning approach to address this problem. We formulate motion planning as a probabilistic-labeled partially observable Markov decision process (PL-POMDP) problem and use linear temporal logic (LTL) to express the complex task. The LTL formula is then converted to a limit-deterministic generalized B\"uchi automaton (LDGBA). The problem is redefined as finding an optimal policy on the product of PL-POMDP with LDGBA based on model-checking techniques to satisfy the complex task. We implement deep Q learning with long short-term memory (LSTM) to process the observation history and task recognition. Our contributions include the proposed method, the utilization of LTL and LDGBA, and the LSTM-enhanced deep Q learning. We demonstrate the applicability of the proposed method by conducting simulations in various environments, including grid worlds, a virtual office, and a multi-agent warehouse. The simulation results demonstrate that our proposed method effectively addresses environment, action, and observation uncertainties. This indicates its potential for real-world applications, including the control of unmanned aerial vehicles (UAVs).

This work investigates the formal policy synthesis of continuous-state stochastic dynamic systems given high-level specifications in linear temporal logic. To learn an optimal policy that maximizes the satisfaction probability, we take a product between a dynamic system and the translated automaton to construct a product system on which we solve an optimal planning problem. Since this product system has a hybrid product state space that results in reward sparsity, we introduce a generalized optimal backup order, in reverse to the topological order, to guide the value backups and accelerate the learning process. We provide the optimality proof for using the generalized optimal backup order in this optimal planning problem. Further, this paper presents an actor-critic reinforcement learning algorithm when topological order applies. This algorithm leverages advanced mathematical techniques and enjoys the property of hyperparameter self-tuning. We provide proof of the optimality and convergence of our proposed reinforcement learning algorithm. We use neural networks to approximate the value function and policy function for hybrid product state space. Furthermore, we observe that assigning integer numbers to automaton states can rank the value or policy function approximated by neural networks. To break the ordinal relationship, we use an individual neural network for each automaton state's value (policy) function, termed modular learning. We conduct two experiments. First, to show the efficacy of our reinforcement learning algorithm, we compare it with baselines on a classic control task, CartPole. Second, we demonstrate the empirical performance of our formal policy synthesis framework on motion planning of a Dubins car with a temporal specification.

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton whose edges are labeled by the task’s subgoals expressed as propositional logic formulas over a set of high-level events. A subgoal automaton also consists of two special states: a state indicating the successful completion of the task, and a state indicating that the task has finished without succeeding. A state-of-the-art inductive logic programming system is used to learn a subgoal automaton that covers the traces of high-level events observed by the RL agent. When the currently exploited automaton does not correctly recognize a trace, the automaton learner induces a new automaton that covers that trace. The interleaving process guarantees the induction of automata with the minimum number of states, and applies a symmetry breaking mechanism to shrink the search space whilst remaining complete. We evaluate ISA in several gridworld and continuous state space problems using different RL algorithms that leverage the automaton structures. We provide an in-depth empirical analysis of the automaton learning performance in terms of the traces, the symmetry breaking and specific restrictions imposed on the final learnable automaton. For each class of RL problem, we show that the learned automata can be successfully exploited to learn policies that reach the goal, achieving an average reward comparable to the case where automata are not learned but handcrafted and given beforehand.

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton whose edges are labeled by the task's subgoals expressed as propositional logic formulas over a set of high-level events. A subgoal automaton also consists of two special states: a state indicating the successful completion of the task, and a state indicating that the task has finished without succeeding. A state-of-the-art inductive logic programming system is used to learn a subgoal automaton that covers the traces of high-level events observed by the RL agent. When the currently exploited automaton does not correctly recognize a trace, the automaton learner induces a new automaton that covers that trace. The interleaving process guarantees the induction of automata with the minimum number of states, and applies a symmetry breaking mechanism to shrink the search space whilst remaining complete. We evaluate ISA in several grid-world and continuous state space problems using different RL algorithms that leverage the automaton structures. We provide an in-depth empirical analysis of the automaton learning process performance in terms of the traces, the symmetric breaking and specific restrictions imposed on the final learnable automaton. For each class of RL problem, we show that the learned automata can be successfully exploited to learn policies that reach the goal, achieving an average reward comparable to the case where automata are not learned but handcrafted and given beforehand.

Our method relies on inducing an automaton whose transitions are subgoals expressed as propositional formulas over a set of observable events. A state-of-the-art inductive logic programming system is used to learn the automaton from observation traces perceived by the RL agent. The reinforcement learning and automaton learning processes are interleaved: a new refined automaton is learned whenever the RL agent generates a trace not recognized by the current automaton. We evaluate ISA in several gridworld problems and show that it performs similarly to a method for which automata are given in advance. We also show that the learned automata can be exploited to speed up convergence through reward shaping and transfer learning across multiple tasks. Finally, we analyze the running time and the number of traces that ISA needs to learn an automata, and the impact that the number of observable events has on the learner's performance.

We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct an on-the-fly synchronised product with the MDP and the finite machine. The temporal structure acts as a guide for the RL agent within the product, where a modular Deep Deterministic Policy Gradient (DDPG) architecture is proposed to generate a low-level control policy. We evaluate our framework in a Mars rover experiment and we present the success rate of the synthesised policy.