Multi-Path Policy Optimization
AAMAS '19: International Conference on Autonomous Agents and Multiagent Systems Auckland New Zealand May, 2020, pp. 1001-1009, 2019.
Recent years have witnessed a tremendous improvement of deep reinforcement learning. However, a challenging problem is that an agent may suffer from inefficient exploration, particularly for on-policy methods. Previous exploration methods either rely on complex structure to estimate the novelty of states, or incur sensitive hyper-paramete...More
PPT (Upload PPT)