Principled Methods for Advising Reinforcement Learning Agents

  title={Principled Methods for Advising Reinforcement Learning Agents},
  author={Eric Wiewiora and Garrison W. Cottrell and Charles Elkan},
An important issue in reinforcement learning is how to incorporate expert knowledge in a principled manner, especially as we scale up to real-world tasks. In this paper, we present a method for incorporating arbitrary advice into the reward structure of a reinforcement learning agent without altering the optimal policy. This method extends the potentialbased shaping method proposed by Ng et al. (1999) to the case of shaping functions based on both states and actions. This allows for much more… CONTINUE READING
Highly Cited
This paper has 75 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.

76 Citations

Citations per Year
Semantic Scholar estimates that this publication has 76 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-9 of 9 references

A framework for the adaptive transfer of robot skill knowledge among reinforcement learning agents

  • R. J. Malak, P. K. Kholsa
  • Robotic Automation,
  • 2001
2 Excerpts

Learning to ride a bicycle using reinforcement learning and shaping

  • J. Randløv, P. Alsrøm
  • Machine Learning, Proceedings of the Fifteenth…
  • 1998
1 Excerpt

Similar Papers

Loading similar papers…