Understand
Reinforcement learning algorithms need to deal with the exponential growth of states and actions when exploring optimal control in high-dimensional spaces.
- This is known as the curse of dimensionality.
- By projecting the agent's state onto a low-dimensional manifold, we can represent the state space in a smaller and more efficient representation.
- By using this representation during learning, the agent can converge to a good policy much faster.
Built on
Face recognition using eigenfaces
M.A. Turk and A.P. Pentland · 1991
Earlier work this paper cites.
A tutorial on principal component analysis
Jonathon Shlens · 2005
Earlier work this paper cites.
Dimensional reduction for reward-based learning, 2005
Christian D. Swinehart and L. F. Abbott · 2005
Earlier work this paper cites.
A survey of robot learning from demonstration
Brenna D. Argall, Sonia Chernova, Manuela Veloso, and Brett Browning · 2008
Earlier work this paper cites.
Similar
A survey on transfer learning
Sinno Jialin Pan and Qiang Yang · 2009
Cited alongside, same era.
Compressive reinforcement learning with oblique random projections, 2011
Bo Liu and Sridhar Mahadevan · 2011
Cited alongside, same era.
The Mario AI benchmark and competitions
Sergey Karakovskiy and Julian Togelius · 2012
Cited alongside, same era.
Cs229 final report reinforcement learning to play mario
Yizheng Liao, Kun Yi, and Zhe Yang · 2012
Cited alongside, same era.
Reinforcement learning with reward shaping and mixed resolution function approximation
M. Grzes and D. Kudenko
Cited in the paper.
Then
Multi-objectivization of reinforcement learning problems by reward shaping
Tim Brys, Anna Harutyunyan, Peter Vrancx, Matthew E Taylor, Daniel Kudenko, and Ann Nowé · 2014
Later among the works it cites.
Learning a super mario controller from examples of human play
Geoffrey Lee, Min Luo, Fabio Zambetta, and Xiaodong Li · 2014
Later among the works it cites.
Reinforcement learning from demonstration through shaping
Tim Brys, Anna Harutyunyan, Halit Bener Suay, Sonia Chernova, Matthew E. Taylor, and Ann Nowé · 2015
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…