Search Results for author:
Found 23 papers, 8 papers with code
Exploration by Learning Diverse Skills through Successor State Measures
We propose a formalization of this search for diverse skills, building on a previous definition based on the mutual information between states and skills.
RRLS : Robust Reinforcement Learning Suite
We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments.
Time-Constrained Robust MDPs
Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates.
Bootstrapping Expectiles in Reinforcement Learning
On robust RL benchmarks, involving changes of the environment, we show that our approach is more robust than classic RL algorithms.
Genetic Drift Regularization: on preventing Actor Injection from breaking Evolution Strategies
Here, we highlight the phenomenon of genetic drift where the actor genome and the ES population distribution progressively drift apart, leading to injection having a negative impact on the ES.
Quality with Just Enough Diversity in Evolutionary Policy Search
Evolution Strategies (ES) are effective gradient-free optimization methods that can be competitive with gradient-based approaches for policy search.
Curiosity creates Diversity in Policy Search
In this work, we use a recently proposed definition of intrinsic motivation, Curiosity, in an evolutionary policy search method.
Neural Distillation as a State Representation Bottleneck in Reinforcement Learning
Learning a good state representation is a critical skill when dealing with multiple tasks in Reinforcement Learning as it allows for transfer and better generalization between tasks.
On Neural Consolidation for Transfer in Reinforcement Learning
Although transfer learning is considered to be a milestone in deep reinforcement learning, the mechanisms behind it are still poorly understood.
Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning
This implies that training of a policy with small generalization gap should focus on such important pixels and ignore the others.
Local Feature Swapping for Generalization in Reinforcement Learning
We also demonstrate the effectiveness of CLOP as a general regularization technique in supervised learning.
When, where, and how to add new neurons to ANNs
Neurogenesis in ANNs is an understudied and difficult problem, even compared to other forms of structural learning like pruning.
Disentanglement by Cyclic Reconstruction
This enables the isolation of task-specific information from both domains and a projection into a common representation.
Large Batch Experience Replay
The optimal sampling distribution being intractable, we make several approximations providing good results in practice and introduce, among others, LaBER (Large Batch Experience Replay), an easy-to-code and efficient method for sampling the replay buffer.
Disentangled cyclic reconstruction for domain adaptation
The domain adaptation problem involves learning a unique classification or regres-sion model capable of performing on both a source and a target domain.
Lipschitz Lifelong Reinforcement Learning
We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks.
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
time; 2) we consider a planning agent using the current model of the environment but unaware of its future evolution.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location
Although presented through the application to the facility location problem, the approach developed here is general and explores a new perspective on the exploitation of past experience in combinatorial optimization.
A Reinforcement Learning Perspective on the Optimal Control of Mutation Probabilities for the (1+1) Evolutionary Algorithm: First Results on the OneMax Problem
We study how Reinforcement Learning can be employed to optimally control parameters in evolutionary algorithms.
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version
time; 2) we consider a planning agent using the current model of the environment but unaware of its future evolution.
Open Loop Execution of Tree-Search Algorithms, extended version
In the context of tree-search stochastic planning algorithms where a generative model is available, we consider on-line planning algorithms building trees in order to recommend an action.
Naive Bayes Classification for Subset Selection
This article focuses on the question of learning how to automatically select a subset of items among a bigger set.
Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring
Autonomous unpowered flight is a challenge for control and guidance systems: all the energy the aircraft might use during flight has to be harvested directly from the atmosphere.
