Recycling Robot Example - aegean.ai

Problem statement

recycling-robot-fsm

Finite State Machine of a a recycling robot and MDP dynamics LUT

Solution

solution

Key references: (Bency et al., 2019; Schmidhuber, 2015; Marco et al., 2017; Hamrick et al., 2017)

References

Bency, M., Qureshi, A., Yip, M. (2019). Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation. arXiv [cs.RO].
Hamrick, J., Ballard, A., Pascanu, R., Vinyals, O., Heess, N., et al. (2017). Metacontrol for Adaptive Imagination-Based Optimization. arXiv [cs.LG].
Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A., Krause, A., et al. (2017). Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization. arXiv [cs.RO].
Schmidhuber, J. (2015). On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models. arXiv [cs.AI].

Edit this page on GitHub or file an issue.