I have uploaded a new video showing how to use redundancy resolution in different policy search methods – including reinforcement learning and evolutions strategies – to embed secondary objectives without any reward shaping. This approach is evaluated in simulation and on the real robot. It focuses on the task of robotic manipulation.
Here it is:
You can also find this project in the highlight section on my main page. Stay tuned as there is coming a more detailed blog in the near future!
Our Paper, Time-Efficient Reinforcement Learning with Stochastic Stateful Policies, was accepted at the International Conference on Learning Representations (ICLR) 2024! We introduce a novel training
Introducing the first imitation learning benchmark tailored towards locomotion. This benchmark comes with many different environments and motion capture dataset facilitating research in locomotion. We
Happy to announce that our work on Least Squares Inverse Q-Learning got accepted to the European Workshop on Reinforcement Learning.