Journal of Machine Learning Research? (2002)??-?? Submitted?/??; Published?/?? ε–MDPs: Learning in Varying Environments

Citations in the corpus

• Benchmarking Deep Reinforcement Learning for Continuous Control (2016, background): “Since we penalize for excessive controls as well as falling over, during the initial stage of learning, when the robot is not yet able to move forward for a sufficient distance without falling, apparent local optima exist including staying at the origin or diving forward slowly.”
• Preparing for the Unknown: Learning a Universal Policy with Online System Identification (2017, background): “One example of such work is the idea of event-learning proposed by Szita et al. [33].”
• Non-Stationary Markov Decision Processes a Worst-Case Approach using Model-Based Reinforcement Learning (2019, background): “Szita et al. [2002] also consider the robust MDP setting and adopt a different constraint hypothesis on the set of possible functions than our LC assumption.”
• A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces (2020, background): “Szita et al. (2002) and Csáji and Monostori (2008) study the convergence of Q-learning when the environment changes but remain close to a fixed MDP. Assuming full knowledge of the MDP at each time step, but with unknown evolution, Lecarpentier and Rachelson (2019) introduce a risk-averse approach to…”