Search Results for author:
Found 14 papers, 5 papers with code
SplAgger: Split Aggregation for Meta-Reinforcement Learning
However, it remains unclear whether task inference sequence models are beneficial even when task inference objectives are not.
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies.
Annotation Sensitivity: Training Data Collection Methods Affect Model Performance
We introduce the term annotation sensitivity to refer to the impact of annotation data collection methods on the annotations themselves and on downstream model performance and predictions.
Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
While many specialized meta-RL methods have been proposed, recent work suggests that end-to-end learning in conjunction with an off-the-shelf sequential model, such as a recurrent network, is a surprisingly strong baseline.
Universal Morphology Control via Contextual Modulation
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control.
A Survey of Meta-Reinforcement Learning
Meta-RL is most commonly studied in a problem setting where, given a distribution of tasks, the goal is to learn a policy that is capable of adapting to any new task from the task distribution with as little data as possible.
Hypernetworks in Meta-Reinforcement Learning
In this paper, we 1) show that hypernetwork initialization is also a critical factor in meta-RL, and that naive initializations yield poor performance; 2) propose a novel hypernetwork initialization scheme that matches or exceeds the performance of a state-of-the-art approach proposed for supervised settings, as well as being simpler and more general; and 3) use this method to show that hypernetworks can improve performance in meta-RL by evaluating on multiple simulated robotics benchmarks.
An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms.
Trust Region Bounds for Decentralized PPO Under Non-stationarity
We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non-stationary.
On the Practical Consistency of Meta-Reinforcement Learning Algorithms
We further find that theoretically inconsistent algorithms can be made consistent by continuing to update all agent components on the OOD tasks, and adapt as well or better than originally consistent ones.
AMRL: Aggregated Memory For Reinforcement Learning
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
Stackelberg Punishment and Bully-Proofing Autonomous Vehicles
This idea generalizes the concept of a Stackelberg equilibrium.
ReNeg and Backseat Driver: Learning from Demonstration with Continuous Human Feedback
Our framework learns continuous control from sub-optimal demonstration and evaluative feedback collected before training.
Neural Mesh: Introducing a Notion of Space and Conservation of Energy to Neural Networks
Like in the brain, we only allow neurons to fire in a time step if they contain enough energy, or excitement.
