Search
Skip to Search Results- 21Bowling, Michael (Computing Science)
- 3Schuurmans, Dale (Computing Science)
- 1Bellemare, Marc (Google Brain)
- 1Greenwald, Amy (Computer Science, Brown University)
- 1Martin, John (Computing Science)
- 1Schuurmans, Dale (Computing Science)
- 2White, Martha
- 1Afkanpour, Arash
- 1Behboudian, Paniz
- 1Burch, Neil
- 1Burega, Bradley Thomas
- 1Cholodovskis Machado, Marlos
- 6Artificial Intelligence
- 6Reinforcement Learning
- 4Machine Learning
- 3Game Theory
- 3Machine learning
- 2Abstractions
-
Spring 2010
In this work, we present a unified, general approach to variance reduction in agent evaluation using machine learning to minimize variance. Evaluating an agent's performance in a stochastic setting is necessary for agent development, scientific evaluation, and competitions. Traditionally,...
-
Fall 2009
For zero-sum games, we have efficient solution techniques. Unfortunately, there are interesting games that are too large to solve. Here, a popular approach is to solve an abstract game that models the original game. We assume that more accurate the abstract games result in stronger strategies....
-
Spring 2016
Monte Carlo methods are a simple, effective, and widely deployed way of approximating integrals that prove too challenging for deterministic approaches. This thesis presents a number of contributions to the field of adaptive Monte Carlo methods. That is, approaches that automatically adjust the...
-
Spring 2015
Much of the focus on finding good representations in reinforcement learning has been on learning complex non-linear predictors of value. Methods like policy gradient, that do not learn a value function and instead directly represent policy, often need fewer parameters to learn good policies....
-
Spring 2024
In model-based reinforcement learning, an agent can improve its policy by planning: learning from experience generated by a model. Search control is the problem of determining which starting state should be used to generate this experience. Given a limited planning budget, an agent should be...
-
Chasing Hallucinated Value: A Pitfall of Dyna Style Algorithms with Imperfect Environment Models
DownloadSpring 2020
In Dyna style algorithms, reinforcement learning (RL) agents use a model of the environment to generate simulated experience. By updating on this simulated experience, Dyna style algorithms allow agents to potentially learn control policies in fewer environment interactions than agents that use...
-
Fall 2019
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the result of specific environmental pressures...
-
Spring 2019
In the reinforcement learning (RL) problem an agent must learn how to act optimally through trial-and-error interactions with a complex, unknown, stochastic environment. The actions taken by the agent influence not just the immediate reward it observes but also the future states and rewards it...
-
Fall 2013
This thesis presents new algorithms for dealing with large scale reinforcement learning problems. Central to this work is the Atari 2600 platform, which acts as both a rich evaluation framework and a source of challenges for existing reinforcement learning methods. Three contributions are...
-
Hindsight Rational Learning for Sequential Decision-Making: Foundations and Experimental Applications
DownloadFall 2022
This thesis develops foundations for the development of dependable, scalable reinforcement learning algorithms with strong connections to game theory. I present a version of rationality for learning---one grounded in the learner's experience and connected with the rationality concepts of...