A PAC learning algorithm for LTL and omega-regular objectives in MDPs
Linear temporal logic (LTL) and omega-regular objectives---a superset of LTL---have seen
recent use as a way to express non-Markovian objectives in reinforcement learning. We …
recent use as a way to express non-Markovian objectives in reinforcement learning. We …
Eventual discounting temporal logic counterfactual experience replay
Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization
that may otherwise be difficult to describe with scalar reward functions. However, the …
that may otherwise be difficult to describe with scalar reward functions. However, the …
Deep Policy Optimization with Temporal Logic Constraints
Temporal logics, such as linear temporal logic (LTL), offer a precise means of specifying
tasks for (deep) reinforcement learning (RL) agents. In our work, we consider the setting …
tasks for (deep) reinforcement learning (RL) agents. In our work, we consider the setting …
Using experience classification for training non-Markovian tasks
Abstract Unlike standard Reinforcement Learning (RL) model, many real-world tasks are
non-Markovian, which requires long-term memory and dependency. Hence solving a non …
non-Markovian, which requires long-term memory and dependency. Hence solving a non …
Directed Exploration in Reinforcement Learning from Linear Temporal Logic
M Bagatella, A Krause, G Martius - arXiv preprint arXiv:2408.09495, 2024 - arxiv.org
Linear temporal logic (LTL) is a powerful language for task specification in reinforcement
learning, as it allows describing objectives beyond the expressivity of conventional …
learning, as it allows describing objectives beyond the expressivity of conventional …
LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
Operating effectively in complex environments while complying with specified constraints is
crucial for the safe and successful deployment of robots that interact with and operate …
crucial for the safe and successful deployment of robots that interact with and operate …
Optimal Control Synthesis of Markov Decision Processes for Efficiency with Surveillance Tasks
We investigate the problem of optimal control synthesis for Markov Decision Processes
(MDPs), addressing both qualitative and quantitative objectives. Specifically, we require the …
(MDPs), addressing both qualitative and quantitative objectives. Specifically, we require the …
Belief-State Query Policies for Planning With Preferences Under Partial Observability
D Bramblett, S Srivastava - arXiv preprint arXiv:2405.15907, 2024 - arxiv.org
Planning in real-world settings often entails addressing partial observability while aligning
with users' preferences. We present a novel framework for expressing users' preferences …
with users' preferences. We present a novel framework for expressing users' preferences …
Characterizing Evolutionary Trends in Temporal Knowledge Graphs with Linear Temporal Logic
Temporal changes in data set the need for the development of knowledge representation
techniques able to capture these dynamics. Temporal Knowledge Graphs (TKGs) have …
techniques able to capture these dynamics. Temporal Knowledge Graphs (TKGs) have …
[PDF][PDF] Robust Reinforcement Learning for Linear Temporal Logic Specifications with Finite Trajectory Duration
SM Moghaddam, YV Pant, S Fischmeister - assets.pubpub.org
Abstract Linear Temporal Logic (LTL), a formal behavioral specification language, offers a
mathematically unambiguous and succinct way to represent operating requirements for a …
mathematically unambiguous and succinct way to represent operating requirements for a …