The optimal policy in various real-world strategic decision-making problems depends both on the environmental configuration and exogenous events.

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited theoretical studies of soft Q-learning to date. This paper aims to offer a novel and unified finite-time, control-theoretic analysis of soft Q-learning algorithms. We focus on two types of soft Q-learning algorithms: one utilizing the log-sum-exp operator and the other employing the Boltzmann operator. By using dynamical switching system models, we derive novel finite-time error bounds for both soft Q-learning algorithms. We hope that our analysis will deepen the current understanding of soft Q-learning by establishing connections with switching system models and may even pave the way for new frameworks in the finite-time analysis of other reinforcement learning algorithms.

In various applications, the optimal policy in a strategic decision-making problem depends both on the environmental configuration and exogenous events. For these settings, we introduce Bilevel Optimization with Contextual Markov Decision Processes (BO-CMDP), a stochastic bilevel decision-making model, where the lower level consists of solving a contextual Markov Decision Process (CMDP). BO-CMDP can be viewed as a Stackelberg Game where the leader and a random context beyond the leader's control together decide the setup of (many) MDPs that (potentially multiple) followers best respond to. This framework extends beyond traditional bilevel optimization and finds relevance in diverse fields such as model design for MDPs, tax design, reward shaping and dynamic mechanism design. We propose a stochastic Hyper Policy Gradient Descent (HPGD) algorithm to solve BO-CMDP, and demonstrate its convergence. Notably, HPGD only utilizes observations of the followers' trajectories. Therefore, it allows followers to use any training procedure and the leader to be agnostic of the specific algorithm used, which aligns with various real-world scenarios. We further consider the setting when the leader can influence the training of followers and propose an accelerated algorithm. We empirically demonstrate the performance of our algorithm.

We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process proportionally to some predefined reward. While we could use maximum entropy Reinforcement Learning (MaxEnt RL) to solve this problem for some distributions, it has been shown that in general, the distribution over states induced by the optimal policy may be biased in cases where there are multiple ways to generate the same object. To address this issue, Generative Flow Networks (GFlowNets) learn a stochastic policy that samples objects proportionally to their reward by approximately enforcing a conservation of flows across the whole Markov Decision Process (MDP). In this paper, we extend recent methods correcting the reward in order to guarantee that the marginal distribution induced by the optimal MaxEnt RL policy is proportional to the original reward, regardless of the structure of the underlying MDP. We also prove that some flow-matching objectives found in the GFlowNet literature are in fact equivalent to well-established MaxEnt RL algorithms with a corrected reward. Finally, we study empirically the performance of multiple MaxEnt RL and GFlowNet algorithms on multiple problems involving sampling from discrete distributions.

Maximum Entropy Reinforcement Learning (MaxEnt RL) algorithms such as Soft Q-Learning (SQL) and Soft Actor-Critic trade off reward and policy entropy, which has the potential to improve training stability and robustness. Most MaxEnt RL methods, however, use a constant tradeoff coefficient (temperature), contrary to the intuition that the temperature should be high early in training to avoid overfitting to noisy value estimates and decrease later in training as we increasingly trust high value estimates to truly lead to good rewards. Moreover, our confidence in value estimates is state-dependent, increasing every time we use more evidence to update an estimate. In this paper, we present a simple state-based temperature scheduling approach, and instantiate it for SQL as Count-Based Soft Q-Learning (CBSQL). We evaluate our approach on a toy domain as well as in several Atari 2600 domains and show promising results.

Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge in exploiting expert demonstrations whilst keeping exploration potentials, especially for value based methods. In this paper, we propose a pretraining method for soft Q-learning. Our work is inspired by pretraining methods for actor-critic algorithms since soft Q-learning is a value based algorithm that is equivalent to policy gradient. The proposed method is based on $\gamma$-discounted biased policy evaluation with entropy regularization, which is also the updating target of soft Q-learning. Our method is evaluated on various tasks from Atari 2600. Experiments show that our method effectively learns from imperfect demonstrations, and outperforms other state-of-the-art methods that learn from expert demonstrations.

Generalization to unknown/uncertain environments of reinforcement learning algorithms is crucial for real-world applications. In this work, we explicitly consider uncertainty associated with the test environment through an uncertainty set. We formulate the Distributionally Robust Reinforcement Learning (DR-RL) objective that consists in maximizing performance against a worst-case policy in uncertainty set centered at the reference policy. Based on this objective, we derive computationally efficient policy improvement algorithm that benefits from Distributionally Robust Optimization (DRO) guarantees. Further, we propose an iterative procedure that increases stability of learning, called Distributionally Robust Policy Iteration. Combined with maximum entropy framework, we derive a distributionally robust variant of Soft Q-learning that enjoys efficient practical implementation and produces policies with robust behaviour at test time. Our formulation provides a unified view on a number of safe RL algorithms and recent empirical successes.

Wang, D., and Liu, Q. Learning to draw samples: With application to amortized MLE for generative adversarial learning.

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and reinforcement learning prohibit tuneable strategies as they seek optimal performance. In this paper, we enable such tuneable behaviour by generalising soft Q-learning to stochastic games, where more than one agent interact strategically. We contribute both theoretically and empirically. On the theory side, we show that games with soft Q-learning exhibit a unique value and generalise team games and zero-sum games far beyond these two extremes to cover a continuous spectrum of gaming behaviour. Experimentally, we show how tuning agents' constraints affect performance and demonstrate, through a neural network architecture, how to reliably balance games with high-dimensional representations.