Deep Reactive Planning in Dynamic Environments
Published in CoRL, 2020
This paper proposes a reactive planning in dynamic environments.
Published in CoRL, 2020
This paper proposes a reactive planning in dynamic environments.
Published in IROS, 2020
This paper proposes to decouple planning and control by combining traditional path planning algorithms, supervised learning (SL) and reinforcement learning (RL) algorithms in a synergistic way. By exploiting waypoints produced from SL, an RL agent easily learns to navigate to arbitrary goal locations, and generalize to novel environments.
Published in ICML, 2020
This paper intentionally increases input dimensionality to improve the performance of Deep RL algorithms. The proposed OFENet significantly improves sample efficiency and final performance of RL algorithms.
Published in IROS, 2019
This paper proposes a RL-based algorithm for trajectory optimization for constrained dynamical systems.