Hierarchical reinforcement learning: A comprehensive survey
Hierarchical Reinforcement Learning (HRL) enables autonomous decomposition of
challenging long-horizon decision-making tasks into simpler subtasks. During the past …
challenging long-horizon decision-making tasks into simpler subtasks. During the past …
Intelligent problem-solving as integrated hierarchical reinforcement learning
According to cognitive psychology and related disciplines, the development of complex
problem-solving behaviour in biological agents depends on hierarchical cognitive …
problem-solving behaviour in biological agents depends on hierarchical cognitive …
Disaster City Digital Twin: A vision for integrating artificial and human intelligence for disaster management
This paper presents a vision for a Disaster City Digital Twin paradigm that can:(i) enable
interdisciplinary convergence in the field of crisis informatics and information and …
interdisciplinary convergence in the field of crisis informatics and information and …
Deep reinforcement learning
SE Li - Reinforcement learning for sequential decision and …, 2023 - Springer
Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …
decision strategies. However, in many cases, it is desirable to learn directly from …
Learning to synthesize programs as interpretable and generalizable policies
Recently, deep reinforcement learning (DRL) methods have achieved impressive
performance on tasks in a variety of domains. However, neural network policies produced …
performance on tasks in a variety of domains. However, neural network policies produced …
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. Instructions are expressed in a well-known formal …
instructions in multi-task environments. Instructions are expressed in a well-known formal …
Hierarchical reinforcement learning by discovering intrinsic options
We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-
agnostic options in a self-supervised manner while jointly learning to utilize them to solve …
agnostic options in a self-supervised manner while jointly learning to utilize them to solve …
Environment generation for zero-shot compositional reinforcement learning
Many real-world problems are compositional–solving them requires completing
interdependent sub-tasks, either in series or in parallel, that can be represented as a …
interdependent sub-tasks, either in series or in parallel, that can be represented as a …
Does zero-shot reinforcement learning exist?
A zero-shot RL agent is an agent that can solve any RL task in a given environment,
instantly with no additional planning or learning, after an initial reward-free learning phase …
instantly with no additional planning or learning, after an initial reward-free learning phase …
Proto: Program-guided transformer for program-guided tasks
Programs, consisting of semantic and structural information, play an important role in the
communication between humans and agents. Towards learning general program executors …
communication between humans and agents. Towards learning general program executors …