Search Results for author:
Found 7 papers, 2 papers with code
Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula
However, this approach produces agents that do not perform robustly in safety-critical settings, an issue that cannot be addressed by simply adding more data to the training set - we show that an agent trained using only a 10% subset of the data performs just as well as an agent trained on the entire dataset.
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving.
Fast Efficient Hyperparameter Tuning for Policy Gradient Methods
The main idea is to use existing trajectories sampled by the policy gradient method to optimise a one-step improvement objective, yielding a sample and computationally efficient algorithm that is easy to implement.
Fast Efficient Hyperparameter Tuning for Policy Gradients
The main idea is to use existing trajectories sampled by the policy gradient method to optimise a one-step improvement objective, yielding a sample and computationally efficient algorithm that is easy to implement.
Learning from Demonstration in the Wild
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical.
Fingerprint Policy Optimisation for Robust Reinforcement Learning
Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator.
Alternating Optimisation and Quadrature for Robust Control
ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy.
