Curiosity-Driven Development of Tool Use Precursors: a Computational Model

By Sébastien Forestier, Pierre-Yves Oudeyer. 2016

28 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Yoan Mollard
2. Sébastien Forestier
3. Brenden M. Lake
4. Josh Tenenbaum
5. German Ignacio Parisi
6. Pierre-Yves Oudeyer
7. Samuel J. Gershman
8. Tomer D. Ullman

Citations in the corpus

• What can the brain teach us about building artificial intelligence? (2016, background): “us action spaces to learn omnidirectional locomotion on slippery surfaces, and versatile manipulation of soft objects (Baranes and Oudeyer, 2013), or hierarchical control of objects through tool use (Forestier and Oudeyer, 2016). Recent work in deep reinforcement learning has included some of these ”
• Continual Lifelong Learning with Neural Networks: A Review (2018, methodology): “French (1997) developed a pseudo-recurrent dual-memory framework, one for early processing and the other for long-termstorage, that usedpseudo-rehearsal (Robins, 1995) to transfer memories between memory centres.”
• Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning (2017, methodology): “Closely related to our work, Forestier and Oudeyer (2016a) extends a former version of our AMB agent in a simulated tool use environment with hierarchical goal spaces, enabling to decompose explicitly trajectory generation.”