Mungojerrie: Reinforcement Learning of Linear-Time Objectives

06/16/2021

∙

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 rewards. Applying this class of algorithms requires designing a reward scheme, which is typically done manually. The designer must ensure that their intent is accurately captured. This may not be trivial, and is prone to error. An alternative to this manual programming, akin to programming directly in assembly, is to specify the objective in a formal language and have it "compiled" to a reward scheme. Mungojerrie (https://plv.colorado.edu/mungojerrie/) is a tool for testing reward schemes for ω-regular objectives on finite models. The tool contains reinforcement learning algorithms and a probabilistic model checker. Mungojerrie supports models specified in PRISM and ω-automata specified in HOA.

READ FULL TEXT

Mungojerrie: Reinforcement Learning of Linear-Time Objectives

Reward Shaping for Reinforcement Learning with Omega-Regular Objectives

Rethinking Expected Cumulative Reward Formalism of Reinforcement Learning: A Micro-Objective Perspective

Distributional Reward Decomposition for Reinforcement Learning

End-to-End Robotic Reinforcement Learning without Reward Engineering

From STL Rulebooks to Rewards

Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion

Modularity benefits reinforcement learning agents with competing homeostatic drives

Mungojerrie: Reinforcement Learning of Linear-Time Objectives

Related Research

Reward Shaping for Reinforcement Learning with Omega-Regular Objectives

Rethinking Expected Cumulative Reward Formalism of Reinforcement Learning: A Micro-Objective Perspective

Distributional Reward Decomposition for Reinforcement Learning

End-to-End Robotic Reinforcement Learning without Reward Engineering

From STL Rulebooks to Rewards

Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion

Modularity benefits reinforcement learning agents with competing homeostatic drives