Search Results for author:
Found 10 papers, 5 papers with code
Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes
Adversarial RCPG also formulates the worst-case dynamics based on the Lagrangian but learns this directly and incrementally as an adversarial policy through gradient descent rather than indirectly and abruptly through constrained optimisation on a sorted value list.
Low Variance Off-policy Evaluation with State-based Importance Sampling
In off-policy reinforcement learning, a behaviour policy performs exploratory interactions with the environment to obtain state-action-reward samples which are then used to learn a target policy that optimises the expected return.
Trust in Language Grounding: a new AI challenge for human-robot teams
The challenge of language grounding is to fully understand natural language by grounding language in real-world referents.
Resilient robot teams: a review integrating decentralised control, change-detection, and learning
Purpose of review: This paper reviews opportunities and challenges for decentralised control, change-detection, and learning in the context of resilient robot teams.
Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time
Constrained Markov decision processes (CMDPs) can provide long-term safety constraints; however, the agent may violate the constraints in an effort to explore its environment.
Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective
To illuminate the elite solutions for a space of behaviours, QD algorithms require the definition of a suitable behaviour space.
Lifetime policy reuse and the importance of task capacity
A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting.
On the use of feature-maps and parameter control for improved quality-diversity meta-evolution
In Quality-Diversity (QD) algorithms, which evolve a behaviourally diverse archive of high-performing solutions, the behaviour space is a difficult design choice that should be tailored to the target application.
Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation
We also investigate disturbances in the operating environment of the swarm, where the swarm has to adapt to drastic changes in the number of resources available in the environment, and to one of the robots behaving disruptively towards the rest of the swarm, with 30 unique conditions for each such perturbation.
QED: using Quality-Environment-Diversity to evolve resilient robot swarms
To allow fault recovery from randomly injected faults to different robots in a swarm, a model-free approach may be preferable due to the accumulation of faults in models and the difficulty to predict the behaviour of neighbouring robots.
