TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving

no code implementations • 31 Mar 2022 • Qichao Zhang, Yinfeng Gao, Yikang Zhang, Youtian Guo, Dawei Ding, Yunpeng Wang, Peng Sun, Dongbin Zhao

In particular, TrajGen consists of the multi-modal trajectory prediction stage and the reinforcement learning based trajectory modification stage.

Autonomous Driving reinforcement-learning +2

Experience Replay More When It's a Key Transition in Deep Reinforcement Learning

no code implementations • 29 Sep 2021 • Youtian Guo, Qi Gao

We propose a experience replay mechanism in Deep Reinforcement Learning based on Add Noise to Noise (AN2N), which requires agent to replay more experience containing key state, abbreviated as Experience Replay More (ERM).

OpenAI Gym reinforcement-learning +1

Exploring More When It Needs in Deep Reinforcement Learning

no code implementations • 28 Sep 2021 • Youtian Guo, Qi Gao

We propose a exploration mechanism of policy in Deep Reinforcement Learning, which is exploring more when agent needs, called Add Noise to Noise (AN2N).

Continuous Control Efficient Exploration +2