Search Results for author:
Found 6 papers, 1 papers with code
Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards
We introduce two key enhancements to PPO: a hybrid policy architecture that combines an offline policy (trained on expert demonstrations) with an online PPO policy, and a reward shaping mechanism using Time Window Temporal Logic (TWTL).
Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning
We advance the state of the art in Boolean composition of learned tasks with three contributions: i) introduce two distinct notions of safety in this framework; ii) show how to enforce either safety semantics, prove correctness (under some assumptions), and analyze the trade-offs between the two safety notions; and iii) extend Boolean composition from discrete action spaces to continuous action spaces.
STL: Surprisingly Tricky Logic (for System Validation)
The ground-truth validity of a specification, subjects' familiarity with formal methods, and subjects' level of education were found to be significant factors in determining validation correctness.
Lightweight Online Learning for Sets of Related Problems in Automated Reasoning
We present Self-Driven Strategy Learning ($\textit{sdsl}$), a lightweight online learning methodology for automated reasoning tasks that involve solving a set of related problems.
Uncertainty Quantification for Recursive Estimation in Adaptive Safety-Critical Control
In this paper, we present a framework for online parameter estimation and uncertainty quantification in the context of adaptive safety-critical control.
Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications
This is achieved by decomposing an infeasible LTL formula into several reach-avoid sub-tasks with shorter horizons, which can be trained in a modular DRL architecture.
