Search Results for author:
Found 13 papers, 8 papers with code
Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior
Recent work has leveraged Knowledge Representation (KR) to provide a symbolic abstraction of aspects of the state that summarize reward-relevant properties of the state-action history and support learning a Markovian decomposition of the problem in terms of an automaton over the KR.
Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions.
Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi.
Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
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
+2
Be Considerate: Objectives, Side Effects, and Deciding How to Act
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.
AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
We introduce an RL-based framework for learning to accomplish tasks in mobile apps.
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments.
Interpretable Sequence Classification via Discrete Optimization
Our automata-based classifiers are interpretable---supporting explanation, counterfactual reasoning, and human-in-the-loop modification---and have strong empirical performance.
Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
First, we propose reward machines, a type of finite state machine that supports the specification of reward functions while exposing reward function structure.
The act of remembering: a study in partially observable reinforcement learning
Learning memoryless policies is efficient and optimal in fully observable environments.
Partially Observable Reinforcement Learning
reinforcement-learning
+1
Learning Reward Machines for Partially Observable Reinforcement Learning
Reward Machines (RMs), originally proposed for specifying problems in Reinforcement Learning (RL), provide a structured, automata-based representation of a reward function that allows an agent to decompose problems into subproblems that can be efficiently learned using off-policy learning.
Partially Observable Reinforcement Learning
Problem Decomposition
+2
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning
In this paper we propose Reward Machines {—} a type of finite state machine that supports the specification of reward functions while exposing reward function structure to the learner and supporting decomposition.
How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval
Consequently, a main conclusion of this work is that general-purpose commonsense ontologies improve performance on visual reasoning tasks when properly filtered to select meaningful visual relations.
