Picture for Sheila A. McIlraith

Sheila A. McIlraith

Reward Machines for Deep RL in Noisy and Uncertain Environments

May 31, 2024
Viaarxiv icon

PRP Rebooted: Advancing the State of the Art in FOND Planning

Dec 20, 2023
Viaarxiv icon

Remembering to Be Fair: On Non-Markovian Fairness in Sequential DecisionMaking (Preliminary Report)

Dec 08, 2023
Viaarxiv icon

Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior

Jan 08, 2023
Figure 1 for Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior
Figure 2 for Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior
Viaarxiv icon

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

Nov 23, 2022
Figure 1 for Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Figure 2 for Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Figure 3 for Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Figure 4 for Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Viaarxiv icon

Learning to Follow Instructions in Text-Based Games

Add code
Nov 08, 2022
Figure 1 for Learning to Follow Instructions in Text-Based Games
Figure 2 for Learning to Follow Instructions in Text-Based Games
Figure 3 for Learning to Follow Instructions in Text-Based Games
Figure 4 for Learning to Follow Instructions in Text-Based Games
Viaarxiv icon

Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks

Add code
Jun 03, 2022
Figure 1 for Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Figure 2 for Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Figure 3 for Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Figure 4 for Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Viaarxiv icon

Learning Reward Machines: A Study in Partially Observable Reinforcement Learning

Add code
Dec 17, 2021
Figure 1 for Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
Figure 2 for Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
Figure 3 for Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
Figure 4 for Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
Viaarxiv icon

AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning

Add code
Jun 06, 2021
Figure 1 for AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
Figure 2 for AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
Figure 3 for AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
Figure 4 for AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
Viaarxiv icon

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

Jun 04, 2021
Figure 1 for Be Considerate: Objectives, Side Effects, and Deciding How to Act
Figure 2 for Be Considerate: Objectives, Side Effects, and Deciding How to Act
Figure 3 for Be Considerate: Objectives, Side Effects, and Deciding How to Act
Figure 4 for Be Considerate: Objectives, Side Effects, and Deciding How to Act
Viaarxiv icon