5 papers · 1 filter
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
Augustinas JuÄas, Yangchen Pan
Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task. Existing cold-start me…
Gradient Residual Connections
Yangchen Pan, Qizhen Ying, Philip Torr +1
Existing work has linked properties of a function's gradient to the difficulty of function approximation. Motivated by these insights, we study how gradient information can be leve…
An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models
Yangchen Pan, Junfeng Wen, Chenjun Xiao +1
In traditional statistical learning, data points are usually assumed to be independently and identically distributed (i.i.d.) following an unknown probability distribution. This pa…
Measures of Variability for Risk-averse Policy Gradient
Yudong Luo, Yangchen Pan, Jiaqi Tan +1
Risk-averse reinforcement learning (RARL) is critical for decision-making under uncertainty, which is especially valuable in high-stake applications. However, most existing works f…
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization
Yudong Luo, Yangchen Pan, Han Wang +2
Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their…