6 citations · 16 across the 14 of their papers we have counts for
14 papers
Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives
Milad Kazemi, Mateo Perez, Fabio Somenzi +3
Recent advances in reinforcement learning (RL) have renewed interest in reward design for shaping agent behavior, but manually crafting reward functions is tedious and error-prone.…
Assume-Guarantee Reinforcement Learning
Milad Kazemi, Mateo Perez, Fabio Somenzi +3
We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environ…
Omega-Regular Decision Processes
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
Regular decision processes (RDPs) are a subclass of non-Markovian decision processes where the transition and reward functions are guarded by some regular property of the past (a l…
A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs
Mateo Perez, Fabio Somenzi, Ashutosh Trivedi
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 int…
Omega-Regular Reward Machines
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
Reinforcement learning (RL) is a powerful approach for training agents to perform tasks, but designing an appropriate reward mechanism is critical to its success. However, in many…
Policy Synthesis and Reinforcement Learning for Discounted LTL
Rajeev Alur, Osbert Bastani, Kishor Jothimurugan +3
The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, L…
Compositional Reinforcement Learning for Discrete-Time Stochastic Control Systems
Abolfazl Lavaei, Mateo Perez, Milad Kazemi +4
We propose a compositional approach to synthesize policies for networks of continuous-space stochastic control systems with unknown dynamics using model-free reinforcement learning…
Recursive Reinforcement Learning
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about rec…
Alternating Good-for-MDP Automata
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
When omega-regular objectives were first proposed in model-free reinforcement learning (RL) for controlling MDPs, deterministic Rabin automata were used in an attempt to provide a…
Mungojerrie: Reinforcement Learning of Linear-Time Objectives
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
Reinforcement learning synthesizes controllers without prior knowledge of the system. At each timestep, a reward is given. The controllers optimize the discounted sum of these rewa…
Model-free Reinforcement Learning for Branching Markov Decision Processes
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
We study reinforcement learning for the optimal control of Branching Markov Decision Processes (BMDPs), a natural extension of (multitype) Branching Markov Chains (BMCs). The state…
Reward Shaping for Reinforcement Learning with Omega-Regular Objectives
E. M. Hahn, M. Perez, S. Schewe +3
Recently, successful approaches have been made to exploit good-for-MDPs automata (Büchi automata with a restricted form of nondeterminism) for model free reinforcement learning, a…
Good-for-MDPs Automata for Probabilistic Analysis and Reinforcement Learning
Ernst Moritz Hahn, Mateo Perez, Fabio Somenzi +3
We characterize the class of nondeterministic -automata that can be used for the analysis of finite Markov decision processes (MDPs). We call these automata `good-for-MDPs' (GFM…
Omega-Regular Objectives in Model-Free Reinforcement Learning
Ernst Moritz Hahn, Mateo Perez, Sven Schewe +3
We provide the first solution for model-free reinforcement learning of ω-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almos…