Reward Machines for Deep RL in Noisy and Uncertain Environments

1 code implementation • 31 May 2024 • Andrew C. Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith

While Reward Machines have been employed in both tabular and deep RL settings, they have typically relied on a ground-truth interpretation of the domain-specific vocabulary that form the building blocks of the reward function.

counterfactual

Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making

1 code implementation • 8 Dec 2023 • Parand A. Alamdari, Toryn Q. Klassen, Elliot Creager, Sheila A. McIlraith

Fair decision making has largely been studied with respect to a single decision.

Decision Making Fairness

Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines

no code implementations • 20 Nov 2022 • Andrew C. Li, Zizhao Chen, Pashootan Vaezipoor, Toryn Q. Klassen, Rodrigo Toro Icarte, Sheila A. McIlraith

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions.

Learning to Follow Instructions in Text-Based Games

1 code implementation • 8 Nov 2022 • Mathieu Tuli, Andrew C. Li, Pashootan Vaezipoor, Toryn Q. Klassen, Scott Sanner, Sheila A. McIlraith

Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language.

Decision Making Instruction Following +2

Learning Reward Machines: A Study in Partially Observable Reinforcement Learning

no code implementations • 17 Dec 2021 • Rodrigo Toro Icarte, Ethan Waldie, Toryn Q. Klassen, Richard Valenzano, Margarita P. Castro, Sheila A. McIlraith

Here we show that RMs can be learned from experience, instead of being specified by the user, and that the resulting problem decomposition can be used to effectively solve partially observable RL problems.

Partially Observable Reinforcement Learning Problem Decomposition +3

Be Considerate: Objectives, Side Effects, and Deciding How to Act

no code implementations • 4 Jun 2021 • Parand Alizadeh Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, Sheila A. McIlraith

We endow RL agents with the ability to contemplate such impact by augmenting their reward based on expectation of future return by others in the environment, providing different criteria for characterizing impact.

Decision Making Reinforcement Learning (RL)

Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

3 code implementations • 6 Oct 2020 • Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Valenzano, Sheila A. McIlraith

First, we propose reward machines, a type of finite state machine that supports the specification of reward functions while exposing reward function structure.

counterfactual Counterfactual Reasoning +4

The act of remembering: a study in partially observable reinforcement learning

no code implementations • 5 Oct 2020 • Rodrigo Toro Icarte, Richard Valenzano, Toryn Q. Klassen, Phillip Christoffersen, Amir-Massoud Farahmand, Sheila A. McIlraith

Learning memoryless policies is efficient and optimal in fully observable environments.

Partially Observable Reinforcement Learning reinforcement-learning +1

Towards the Role of Theory of Mind in Explanation

no code implementations • 6 May 2020 • Maayan Shvo, Toryn Q. Klassen, Sheila A. McIlraith

Theory of Mind is commonly defined as the ability to attribute mental states (e. g., beliefs, goals) to oneself, and to others.

Attribute