7 papers
About Time: Model-free Reinforcement Learning with Timed Reward Machines
Rajarshi Roy, Anirban Majumdar, Ritam Raha +2
Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have be…
MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
Ashwani Anand, Ivi Chatzi, Ritam Raha +1
Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents…
Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic
Ritam Raha, Rajarshi Roy, Nathanaël Fijalkow +1
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 m…
Follow the STARs: Dynamic -Regular Shielding of Learned Policies
Ashwani Anand, Satya Prakash Nayak, Ritam Raha +1
This paper presents a novel dynamic post-shielding framework that enforces the full class of -regular correctness properties over pre-computed probabilistic policies. This cons…
Maximal Adaptation, Minimal Guidance: Permissive Reactive Robot Task Planning with Humans in the Loop
Oz Gitelson, Satya Prakash Nayak, Ritam Raha +1
We present a novel framework for human-robot \emph{logical} interaction that enables robots to reliably satisfy (infinite horizon) temporal logic tasks while effectively collaborat…
Quantitative Strategy Templates
Ashwani Anand, Satya Prakash Nayak, Ritam Raha +2
This paper presents (permissive) \emph{Quantitative Strategy Templates} (QaSTels) to succinctly represent infinitely many winning strategies in two-player energy and mean-payoff ga…