Evan Greensmith

Publication List Details

Period

2002 - 2005

Number

9

Co-Authors

Policy gradient methods: variance reduction and stochastic convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence (2005)

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning (2002)

Evan Greensmith, Peter L. Bartlett, Jonathan Baxter

We consider the use of two additive control variate methods to reduce the variance of performance gradient estimates in reinforcement learning problems. The first approach we consider is the baseline...

Policy Gradient Methods: Variance Reduction and Stochastic Convergence

Greensmith, Evan

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies,...