M Henaff - Advances in Neural Information Processing …, 2019 - proceedings.neurips.cc
We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state …
L Kuvayev, RS Sutton - Proceedings of the ninth Yale workshop on …, 1996 - Citeseer
Abstract Model-based reinforcement learning, in which a model of the environment's dynamics is learned and used to supplement direct learning from experience, has been …
We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set) …
P Abbeel, M Quigley, AY Ng - … of the 23rd international conference on …, 2006 - dl.acm.org
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or" simulator") of the Markov decision process. However, for high …
Potential-based shaping was designed as a way of introducing background knowledge into model-free reinforcement-learning algorithms. By identifying states that are likely to have …
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample …
Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (eg DBNs) can be learned with tractable sample …
Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model …
In many practical applications of RL, it is expensive to observe state transitions from the environment. For example, in the problem of plasma control for nuclear fusion, computing …