Juan Sebastian Rojas

Juan Sebastian Rojas, Chi-Guhn Lee

The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have been used interchangeably in the literature, with the latter eventually being adopted as the standard critic loss in deep reinforcement learning (RL) architectures. In this work, we show that these two interpretations of the TD error are not always equivalent. In particular, we show that increasingly-nonlinear deep RL architectures can cause these interpretations of the TD error to yield increasingly different numerical values. Then, building on this insight, we show how choosing one interpretation of the TD error over the other can affect the performance of deep RL algorithms that utilize the TD error to compute other quantities, such as with deep differential (i.e., average-reward) RL methods. All in all, our results show that the default interpretation of the TD error as the difference between a bootstrapped target and a prediction does not always hold in deep RL settings.

Juan Sebastian Rojas, Chi-Guhn Lee

Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with the majority of RL-based efforts having been allocated to discounted MDPs. In this work, we study a unique structural property of average-reward MDPs and utilize it to introduce Reward-Extended Differential (or RED) reinforcement learning: a novel RL framework that can be used to effectively and efficiently solve various learning objectives, or subtasks, simultaneously in the average-reward setting. We introduce a family of RED learning algorithms for prediction and control, including proven-convergent algorithms for the tabular case. We then showcase the power of these algorithms by demonstrating how they can be used to learn a policy that optimizes, for the first time, the well-known conditional value-at-risk (CVaR) risk measure in a fully-online manner, without the use of an explicit bi-level optimization scheme or an augmented state-space.

Jacob Adamczyk, Juan Sebastian Rojas, Rahul V. Kulkarni

Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In this work, we follow this tradition by leveraging results from non-equilibrium thermodynamics to formalize curriculum learning in reinforcement learning (RL). In particular, we propose a geometric framework for RL by interpreting reward parameters as coordinates on a task manifold. We show that, by minimizing the excess thermodynamic work, optimal curricula correspond to geodesics in this task space. As an application of this framework, we provide an algorithm, "MEW" (Minimum Excess Work), to derive a principled schedule for temperature annealing in maximum-entropy RL.

Juan Sebastian Rojas, Chi-Guhn Lee

Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful balance between retaining useful information and adapting to new situations. To date, continual RL has been explored almost exclusively through the lens of risk-neutral decision-making, in which the agent aims to optimize the expected (or mean) long-run performance. In this work, we present the first formal theoretical treatment of continual RL through the lens of risk-aware decision-making, in which the agent aims to optimize a reward-based measure of long-run performance beyond the mean. In particular, we show that the classical theory of risk measures, widely used as a theoretical foundation in non-continual risk-aware RL, is, in its current form, incompatible with the continual setting. Then, building on this insight, we extend risk measure theory into the continual setting by introducing a new class of ergodic risk measures that are compatible with continual learning. Finally, we provide a case study of risk-aware continual learning, along with empirical results, which show the intuitive appeal and theoretical soundness of ergodic risk measures.

Juan Sebastian Rojas, Chi-Guhn Lee

To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a potentially-discounted sum of rewards over time. In this work, we extend distributional RL to the average-reward setting, where an agent aims to optimize the reward received per time-step. In particular, we utilize a quantile-based approach to develop the first set of algorithms that can successfully learn and/or optimize the long-run per-step reward distribution, as well as the differential return distribution of an average-reward MDP. We derive proven-convergent tabular algorithms for both prediction and control, as well as a broader family of algorithms that have appealing scaling properties. Empirically, we find that these algorithms consistently yield competitive performance when compared to their non-distributional equivalents, while also capturing rich information about the long-run reward and return distributions.