Theoretical and empirical analysis of reward shaping in reinforcement learning

M Grzes, D Kudenko - 2009 International Conference on …, 2009 - ieeexplore.ieee.org
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …
被引用次数：52 相关文章

Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

M Grzes, D Kudenko - 2009 International Conference on Machine Learning … - infona.pl
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …

Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

M Grzes, D Kudenko - Machine Learning and Applications, Fourth …, 2009 - computer.org
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …

Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

M Grzes, D Kudenko - … of the 2009 International Conference on Machine …, 2009 - dl.acm.org
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …
[PDF] researchgate.net

[PDF][PDF] Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

M Grzes, D Kudenko - researchgate.net
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …

Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning

M Grzes, D Kudenko - 2009 - pure.york.ac.uk
Reinforcement learning suffers scalability problems due to the state space explosion and the
temporal credit assignment problem. Knowledge-based approaches have received a …