226 papers with code • 64 benchmarks • 6 datasets
The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.
( Image credit: Playing Atari with Deep Reinforcement Learning )
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.
We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.
In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x, y) Cartesian space and one-hot pixel space.
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.