Search Results for author:
Found 18 papers, 8 papers with code
Monte Carlo Tree Search with Boltzmann Exploration
Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound applied to Trees (UCT), are instrumental to automated planning techniques.
JaxMARL: Multi-Agent RL Environments in JAX
This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL.
Effects of Explanation Specificity on Passengers in Autonomous Driving
In this paper, we investigate the effects of natural language explanations' specificity on passengers in autonomous driving.
A Framework for Learning from Demonstration with Minimal Human Effort
In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time.
DITTO: Offline Imitation Learning with World Models
We propose DITTO, an offline imitation learning algorithm which uses world models and on-policy reinforcement learning to addresses the problem of covariate shift, without access to an oracle or any additional online interactions.
One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
Our model-based approach is risk-averse to both epistemic and aleatoric uncertainty.
RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning
Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy optimisation within that model, have emerged as a promising approach to this problem.
Beta Residuals: Improving Fault-Tolerant Control for Sensory Faults via Bayesian Inference and Precision Learning
Model-based fault-tolerant control (FTC) often consists of two distinct steps: fault detection & isolation (FDI), and fault accommodation.
Planning for Risk-Aversion and Expected Value in MDPs
This motivates us to propose a lexicographic approach which minimises the expected cost subject to the constraint that the CVaR of the total cost is optimal.
On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
Previous work on planning as active inference addresses finite horizon problems and solutions valid for online planning.
Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inference
This work presents a fault-tolerant control scheme for sensory faults in robotic manipulators based on active inference.
Risk-Averse Bayes-Adaptive Reinforcement Learning
In this work, we address risk-averse Bayes-adaptive reinforcement learning.
Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes
We propose a dynamic programming algorithm that utilises the regret Bellman equation, and show that it optimises minimax regret exactly for UMDPs with independent uncertainties.
Active Inference for Integrated State-Estimation, Control, and Learning
This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators.
Robotics
Convex Hull Monte-Carlo Tree Search
This work investigates Monte-Carlo planning for agents in stochastic environments, with multiple objectives.
Artificial Intelligence for Long-Term Robot Autonomy: A Survey
Autonomous systems will play an essential role in many applications across diverse domains including space, marine, air, field, road, and service robotics.
Simultaneous Task Allocation and Planning Under Uncertainty
We propose novel techniques for task allocation and planning in multi-robot systems operating in uncertain environments.
Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work
We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.
