5 papers
Model-Based Exploration in Monitored Markov Decision Processes
Alireza Kazemipour, Simone Parisi, Matthew E. Taylor +1
A tenet of reinforcement learning is that the agent always observes rewards. However, this is not true in many realistic settings, e.g., a human observer may not always be availabl…
Toward Agents That Reason About Their Computation
Adrian Orenstein, Jessica Chen, Gwyneth Anne Delos Santos +2
While reinforcement learning agents can achieve superhuman performance in many complex tasks, they typically do not become more computationally efficient as they improve. In contra…
Generalization in Monitored Markov Decision Processes (Mon-MDPs)
Montaser Mohammedalamen, Michael Bowling
Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior…
KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation
Jiabin Fan, Guoqing Luo, Michael Bowling +1
We propose a novel k-step return estimation method (called KETCHUP) for Reinforcement Learning(RL)-based knowledge distillation (KD) in text generation tasks. Our idea is to induce…
Beyond Optimism: Exploration With Partially Observable Rewards
Simone Parisi, Alireza Kazemipour, Michael Bowling
Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent le…