Search Results for author:
Found 15 papers, 3 papers with code
Variational Inference for Model-Free and Model-Based Reinforcement Learning
And second, in model-based RL where agents aim to learn about the environment they are operating in, the model-learning part can be naturally phrased as an inference problem over the process that governs environment dynamics.
GPflux: A Library for Deep Gaussian Processes
GPflux is compatible with and built on top of the Keras deep learning eco-system.
Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
This paves the way for new research directions, e. g. investigating uncertainty-aware environment models that are not necessarily neural-network-based, or developing algorithms to solve industrially-motivated benchmarks that share characteristics with real-world problems.
Model-based Reinforcement Learning
reinforcement-learning
+2
A Tutorial on Sparse Gaussian Processes and Variational Inference
In this context, a convenient choice for approximate inference is variational inference (VI), where the problem of Bayesian inference is cast as an optimization problem -- namely, to maximize a lower bound of the log marginal likelihood.
Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
While this has been initially proposed for Markov Decision Processes (MDPs) in tabular settings, it was recently shown that a similar principle leads to significant improvements over vanilla SQL in RL for high-dimensional domains with discrete actions and function approximators.
A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
In this paper, we investigate the use of empowerment in the presence of an extrinsic reward signal.
Soft Q-Learning with Mutual-Information Regularization
We show that the prior optimization introduces a mutual-information regularizer in the RL objective.
Uncertainty in Neural Networks: Approximately Bayesian Ensembling
Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian.
Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks
This paper proposes a new optimization objective for value-based deep reinforcement learning.
An information-theoretic on-line update principle for perception-action coupling
Here we consider perception and action as two serial information channels with limited information-processing capacity.
Balancing Two-Player Stochastic Games with Soft Q-Learning
Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers.
An Information-Theoretic Optimality Principle for Deep Reinforcement Learning
Different learning outcomes can be demonstrated by tuning a Lagrange multiplier accordingly.
A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown.
Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes
As limit cases, this generalized scheme includes standard value iteration with a known model, Bayesian MDP planning, and robust planning.
Bounded Rational Decision-Making in Feedforward Neural Networks
Bounded rational decision-makers transform sensory input into motor output under limited computational resources.
