Search Results for author:
Found 4 papers, 2 papers with code
Evaluating Continual Learning on a Home Robot
Robots in home environments need to be able to learn new skills continuously as data becomes available, becoming ever more capable over time while using as little real-world data as possible.
Spatial-Language Attention Policies for Efficient Robot Learning
We see a 4x improvement over baseline in mobile manipulation setting.
Self-Activating Neural Ensembles for Continual Reinforcement Learning
The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents.
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents
In this work, we present CORA, a platform for Continual Reinforcement Learning Agents that provides benchmarks, baselines, and metrics in a single code package.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
