This is a decommissioned version of ERA which is running to enable completion of migration processes. All new collections and items and all edits to existing items should go to our new ERA instance at https://ualberta.scholaris.ca - Please contact us at erahelp@ualberta.ca for assistance!
Search
Skip to Search Results- 11Planning
- 5Reinforcement Learning
- 4Heuristic Search
- 3Artificial Intelligence
- 2Model-Based Reinforcement Learning
- 1Abstraction
-
Fall 2022
In this thesis, we investigate the empirical performance of several experience replay techniques. Efficient experience replay plays an important role in model-free reinforcement learning by improving sample efficiency through reusing past experience. However, replay-based methods were largely...
-
Fall 2010
We investigate the use of machine learning to create effective heuristics for single-agent search. Our method aims to generate a sequence of heuristics from a given weak heuristic h{0} and a set of unlabeled training instances using a bootstrapping procedure. The training instances that can be...
-
Fall 2013
Many important problems can be cast as state-space problems. In this dissertation we study a general paradigm for solving state-space problems which we name Cluster-and-Conquer (C&C). Algorithms that follow the C&C paradigm use the concept of equivalent states to reduce the number of states...
-
Spring 2016
This thesis proposes, analyzes and tests different exploration-based techniques in Greedy Best-First Search (GBFS) for satisficing planning. First, we show the potential of exploration-based techniques by combining GBFS and random walk exploration locally. We then conduct deep analysis on how...
-
Fall 2024
Planning and goal-conditioned reinforcement learning aim to create more efficient and scalable methods for complex, long-horizon tasks. These approaches break tasks into manageable subgoals and leverage prior knowledge to guide learning. However, learned models may predict inaccurate next states...
-
Fall 2022
This thesis investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives,...
-
Spring 2016
In model-based reinforcement learning a model is learned which is then used to find good actions. What model to learn? We investigate these questions in the context of two different approaches to model-based reinforcement learning. We also investigate how one should learn and plan when the reward...
-
On Efficient Planning in Large Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
DownloadFall 2023
A practical challenge in reinforcement learning is large action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly optimize a global reward function, which leads to a blow-up in the...
-
Strengths, Weaknesses, and Combinations of Model-based and Model-free Reinforcement Learning
DownloadSpring 2016
Reinforcement learning algorithms are conventionally divided into two approaches: a model-based approach that builds a model of the environment and then computes a value function from the model, and a model-free approach that directly estimates the value function. The first contribution of this...
-
Spring 2023
AlphaZero is a self-play reinforcement learning algorithm that achieves superhuman play in the games of chess, shogi, and Go via policy iteration. To be an effective policy improvement operator, AlphaZero’s search needs to have accurate value estimates for the states that appear in its search...