Marcelo Li Koga

According to our database, Marcelo Li Koga authored at least 3 papers between 2013 and 2015.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2015

Stochastic Abstract Policies: Generalizing Knowledge to Improve Reinforcement Learning.

Marcelo Li Koga, Valdinei Freire da Silva, Anna Helena Reali Costa

IEEE Trans. Cybern., 2015

2013

Reusing Risk-Aware Stochastic Abstract Policies in Robotic Navigation Learning.

Valdinei Freire da Silva, Marcelo Li Koga, Fábio Gagliardi Cozman, Anna Helena Reali Costa

Proceedings of the RoboCup 2013: Robot World Cup XVII [papers from the 17th Annual RoboCup International Symposium, 2013

Speeding-up reinforcement learning through abstraction and transfer learning.

Marcelo Li Koga, Valdinei Freire da Silva, Fábio Gagliardi Cozman, Anna Helena Reali Costa

Proceedings of the International conference on Autonomous Agents and Multi-Agent Systems, 2013