Search Results for author:
Found 21 papers, 8 papers with code
Model-based Offline Quantum Reinforcement Learning
The policy is optimized with a gradient-free optimization scheme using the return estimate given by the model as the fitness function.
Learning Control Policies for Variable Objectives from Offline Data
Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available.
Automatic Trade-off Adaptation in Offline RL
Recently, offline RL algorithms have been proposed that remain adaptive at runtime.
Safe Policy Improvement Approaches and their Limitations
Based on this finding, we develop adaptations, the Adv-Soft-SPIBB algorithms, and show that they are provably safe.
Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning
We present a full implementation and simulation of a novel quantum reinforcement learning method.
User-Interactive Offline Reinforcement Learning
At the same time, offline RL algorithms are not able to tune their most important hyperparameter - the proximity of the learned policy to the original policy.
Safe Policy Improvement Approaches on Discrete Markov Decision Processes
Safe Policy Improvement (SPI) aims at provable guarantees that a learned policy is at least approximately as good as a given baseline policy.
Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning
Offline reinforcement learning (RL) Algorithms are often designed with environments such as MuJoCo in mind, in which the planning horizon is extremely long and no noise exists.
Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning
Recently developed offline reinforcement learning algorithms have made it possible to learn policies directly from pre-collected datasets, giving rise to a new dilemma for practitioners: Since the performance the algorithms are able to deliver depends greatly on the dataset that is presented to them, practitioners need to pick the right dataset among the available ones.
Behavior Constraining in Weight Space for Offline Reinforcement Learning
In offline reinforcement learning, a policy needs to be learned from a single pre-collected dataset.
Overcoming Model Bias for Robust Offline Deep Reinforcement Learning
State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations.
Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming
Autonomously training interpretable control strategies, called policies, using pre-existing plant trajectory data is of great interest in industrial applications.
Interpretable Policies for Reinforcement Learning by Genetic Programming
Here we introduce the genetic programming for reinforcement learning (GPRL) approach based on model-based batch reinforcement learning and genetic programming, which autonomously learns policy equations from pre-existing default state-action trajectory samples.
Sensitivity Analysis for Predictive Uncertainty in Bayesian Neural Networks
We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty.
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Bayesian neural networks with latent variables are scalable and flexible probabilistic models: They account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns in the data.
A Benchmark Environment Motivated by Industrial Control Problems
On one hand, these benchmarks are designed to provide interpretable RL training scenarios and detailed insight into the learning process of the method on hand.
Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data.
Batch Reinforcement Learning on the Industrial Benchmark: First Experiences
The Particle Swarm Optimization Policy (PSO-P) has been recently introduced and proven to produce remarkable results on interacting with academic reinforcement learning benchmarks in an off-policy, batch-based setting.
Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies
To the best of our knowledge, this approach is the first to relate self-organizing fuzzy controllers to model-based batch RL.
Introduction to the "Industrial Benchmark"
A novel reinforcement learning benchmark, called Industrial Benchmark, is introduced.
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning.
Model-based Reinforcement Learning
reinforcement-learning
+2
