Matthew Riemer

hierarchical reinforcement learning (4) temporal abstraction (4) reinforcement learning (3) option learning (3) catastrophic forgetting (2) multi-agent reinforcement learning (2) policy gradient (2) multiagent reinforcement learning (2) partially observable environment (2) large language model (2) mixing time (2) average reward (2) attention mechanism (1) direct preference optimization (1) function approximation (1) policy evaluation (1) natural language processing (1) preference optimization (1) policy optimization (1) continual learning (1)