Search Results for author:
Found 8 papers, 5 papers with code
PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining
A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations.
Safe Reinforcement Learning by Imagining the Near Future
Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences.
Model-based Adversarial Meta-Reinforcement Learning
When the test task distribution is different from the training task distribution, the performance may degrade significantly.
MOPO: Model-based Offline Policy Optimization
We also characterize the trade-off between the gain and risk of leaving the support of the batch data.
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning
We then adapt the dynamical model with samples from this policy in the real environment.
Learning Robotic Assembly from CAD
We propose to leverage this prior knowledge by guiding RL along a geometric motion plan, calculated using the CAD data.
Learning from the Hindsight Plan -- Episodic MPC Improvement
To bring the next real-world execution closer to the hindsight plan, our approach learns to re-shape the original cost function with the goal of satisfying the following property: short horizon planning (as realistic during real executions) with respect to the shaped cost should result in mimicking the hindsight plan.
Value Iteration Networks
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within.
