Bayes-Adaptive Simulation-based Search with Value Function Approximation

By Arthur Guez, Nicolas Manfred Otto Heess, David Silver, Peter S. Dayan. 2014

32 citations recorded by the source corpus.

How researchers see this paper

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

1. Sergey Levine
2. Pieter Abbeel
3. Yoshua Bengio
4. Chelsea Finn
5. Ruslan Salakhutdinov
6. Trevor Darrell
7. Abhishek Gupta
8. Abhinav Kumar Gupta

Citations in the corpus

• Deep Exploration via Bootstrapped DQN (2016, methodology): “Other approaches aim to approximate Bayes-optimal exploration though tree-based search (Wang et al., 2005; Guez et al., 2014).”
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning (2016, neutral): “Bayesian RL methods [9, 11, 16, 35], which keep track of a distribution over MDPs, are an alternative to optimism-based methods.”
• Risk-Averse Bayes-Adaptive Reinforcement Learning (2021, background): “(2015b) with the vectorised belief representation for BAMDPs proposed in (Guez et al., 2014) with linear function approximation.”
• VIME: Variational Information Maximizing Exploration (2016, background): “However, these heuristics exhibit random walk exploratory behavior, which can lead to exponential regret even in case of small MDPs [9].”
• Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks (2016, background): “An alternative approach is Bayesian reinforcement learning methods, which maintain a distribution over possible MDPs [1, 17, 23, 31].”