4 papers
Predictive Control Using Learned State Space Models via Rolling Horizon Evolution
Alvaro Ovalle, Simon M. Lucas
A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Ass…
Generalising Discrete Action Spaces with Conditional Action Trees
Christopher Bamford, Alvaro Ovalle
There are relatively few conventions followed in reinforcement learning (RL) environments to structure the action spaces. As a consequence the application of RL algorithms to tasks…
Modulation of viability signals for self-regulatory control
Alvaro Ovalle, Simon M. Lucas
We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisa…
Bootstrapped model learning and error correction for planning with uncertainty in model-based RL
Alvaro Ovalle, Simon M. Lucas
Having access to a forward model enables the use of planning algorithms such as Monte Carlo Tree Search and Rolling Horizon Evolution. Where a model is unavailable, a natural aim i…