Source Themes

Safe and Efficient Reinforcement Learning for Behavioural Planning in Autonomous Driving

In this Ph.D. thesis, we study how autonomous vehicles can learn to act *safely* and avoid accidents, despite sharing the road with human drivers whose behaviours are uncertain. To explicitly account for this uncertainty, informed by online …

Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

We consider the problem of robust and adaptive model predictive control (MPC) of a linear system, with unknown parameters that are learned along the way (adaptive), in a critical setting where failures must be prevented (robust). This problem has …

Planning in Markov Decision Processes with Gap-Dependent Sample Complexity

We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an upper bound on the number of calls to the generative models needed for …

Monte-Carlo Graph Search: the Value of Merging Similar States

We consider the problem of planning in a Markov Decision Process (MDP) with a generative model and limited computational budget. Despite the underlying MDP transitions having a graph structure, the popular Monte-Carlo Tree Search algorithms such as …

Fast active learning for pure exploration in reinforcement learning

Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on exploring …

Adaptive Reward-Free Exploration

Reward-free exploration is a reinforcement learning setting recently studied by Jin et al., who address it by running several algorithms with regret guarantees in parallel. In our work, we instead propose a more adaptive approach for reward-free …

Social Attention for Autonomous Decision-Making in Dense Traffic

An attention architecture for behavioural planning with multiple agents.

Budgeted Reinforcement Learning in Continuous State Space

A scalable algorithm for model-free budgeted RL in continuous state spaces.

Approximate Robust Control of Uncertain Dynamical Systems

Safe control of large non-linear systems operating in uncertain environments.