Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations

Chou, Glen; Özay, Necmiye; Berenson, Dmitry

doi:10.15607/rss.2020.xvi.097

Cited by 20 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…logic or automata, which admit well defined compositions and explicitly encode temporal constraints. The development of this literature mirrors the historical path taken in reward based research, with works adapting optimal control [7,2], Bayesian [11,17], and maximum entropy approaches [14,15] IRL approaches.…”

Section: Related Workmentioning

confidence: 96%

“…In particular, and in contrast to the reward setting, the discrete nature of automata and logic, combined with the assumed a-priori ignorance of the relevant memory required to describe the task, makes existing gradient based approaches either intractable or inapplicable. Instead, current literature either enumerates concepts [14,2,11,17] or hill climbs via simple probabilistic mutations [7,1].…”

Section: Related Workmentioning

confidence: 99%

“…For the incremental experiment, a counterexample loop is used add labeled examples that bias the DFAs towards implying ϕ1 2. Nevertheless, for the monolothic experiment, the wall clock times for DISS, random pivoting, and enumeration were 542s, 764s, and 617s respectively.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Surprise-Guided Search for Learning Task Specifications from Demonstrations

Vazquez-Chanlatte¹,

Shah²,

Lederman³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper considers the problem of learning history dependent task specifications, e.g. automata and temporal logic, from expert demonstrations. Unfortunately, the (countably infinite) number of tasks under consideration combined with an a-priori ignorance of what historical features are needed to encode the demonstrated task makes existing approaches to learning tasks from demonstrations inapplicable. To address this deficit, we propose Demonstration Informed Specification Search (DISS): a family of algorithms parameterized by black box access to (i) a maximum entropy planner and (ii) an algorithm for identifying concepts, e.g., automata, from labeled examples. DISS works by alternating between (i) conjecturing labeled examples to make the demonstrations less surprising and (ii) sampling concepts consistent with the current labeled examples. In the context of tasks described by deterministic finite automata, we provide a concrete implementation of DISS that efficiently combines partial knowledge of the task and a single expert demonstration to identify the full task specification.

show abstract

Section: Related Workmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Surprise-Guided Search for Learning Task Specifications from Demonstrations

Vazquez-Chanlatte¹,

Shah²,

Lederman³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…They search for automata using DPLL search. [10] learns an LTL formula and proposition mapping from demonstrations. Their approach relies on counterexample generation and testing.…”

Section: Related Workmentioning

confidence: 99%

Learning Policies by Learning Rules

Araki

Choi

Chin

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Efficiently learning interpretable policies for complex tasks from demonstrations is a challenging problem. We present Hierarchical Inference with Logical Options (HILO), a novel learning algorithm that learns to imitate expert demonstrations by learning the rules that the expert is following. The rules are represented as linear temporal logic (LTL) formulas, which are interpretable and capable of encoding complex behaviors. Unlike previous works, which learn rules from highlevel propositions, HILO learns rules by taking both propositions and low-level trajectories as input. It does this by defining a Bayesian model over LTL formulas, propositions, and low-level trajectories. The Bayesian model bridges the gap from formula to low-level trajectory by using a planner to find an optimal policy for a given LTL formula. Stochastic variational inference is then used to find a posterior distribution over formulas and policies given expert demonstrations. We show that by learning rules from both propositions and low-level states, HILO outperforms previous work on a rule-learning task and on four planning tasks while needing less data. We also validate HILO in the real world by teaching a robotic arm a complex packing task.

show abstract

“…Applications include program specification [20], anomaly and fault detection [4], robotics [6], and many more: we refer to [5], Section 7, for a list of practical applications. An equivalent point of view on LTL learning is as a specification mining question.…”

Section: State Of the Artmentioning

confidence: 99%

Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic

Raha¹,

Roy²,

Fijalkow³

et al. 2021

Preprint

View full text Add to dashboard Cite

Linear temporal logic (LTL) is a specification language for finite sequences (called traces) widely used in program verification, motion planning in robotics, process mining, and many other areas. We consider the problem of learning LTL formulas for classifying traces; despite a growing interest of the research community existing solutions suffer from two limitations: they do not scale beyond small formulas, and they may exhaust computational resources without returning any result. We introduce a new algorithm addressing both issues: our algorithm is able to construct formulas an order of magnitude larger than previous methods, and it is anytime, meaning that it in most cases successfully outputs a formula, albeit possibly not of minimal size. We evaluate the performances of our algorithm using an open source implementation against publicly available benchmarks.

show abstract

Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations

Cited by 20 publications

References 32 publications

Surprise-Guided Search for Learning Task Specifications from Demonstrations

Surprise-Guided Search for Learning Task Specifications from Demonstrations

Learning Policies by Learning Rules

Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic

Contact Info

Product

Resources

About