Can replay, as a widely observed neural activity pattern in brain regions, particularly in the hippocampus and neocortex, emerge in an artificial agent? If yes, does it contribute to the tasks? In this work, without heavy dependence on complex assumptions, we discover naturally emergent replay under task-optimized paradigm using a recurrent neural network-based reinforcement learning model, which mimics the hippocampus and prefrontal cortex, as well as their intercommunication and the sensory cortex input. The emergent replay in the hippocampus, which results from the episodic memory and cognitive map as well as environment observations, well resembles animal experimental data and serves as an effective indicator of high task performance. The model also successfully reproduces local and nonlocal replay, which matches the human experimental data. Our work provides a new avenue for understanding the mechanisms behind replay.

This study introduces a novel approach to autonomous motion planning, informing an analytical algorithm with a reinforcement learning (RL) agent within a Frenet coordinate system. The combination directly addresses the challenges of adaptability and safety in autonomous driving. Motion planning algorithms are essential for navigating dynamic and complex scenarios. Traditional methods, however, lack the flexibility required for unpredictable environments, whereas machine learning techniques, particularly reinforcement learning (RL), offer adaptability but suffer from instability and a lack of explainability. Our unique solution synergizes the predictability and stability of traditional motion planning algorithms with the dynamic adaptability of RL, resulting in a system that efficiently manages complex situations and adapts to changing environmental conditions. Evaluation of our integrated approach shows a significant reduction in collisions, improved risk management, and improved goal success rates across multiple scenarios. The code used in this research is publicly available as open-source software and can be accessed at the following link: https://github.com/TUM-AVS/Frenetix-RL.

We propose the integration of sentiment analysis and deep-reinforcement learning ensemble algorithms for stock trading, and design a strategy capable of dynamically altering its employed agent given concurrent market sentiment. In particular, we create a simple-yet-effective method for extracting news sentiment and combine this with general improvements upon existing works, resulting in automated trading agents that effectively consider both qualitative market factors and quantitative stock data. We show that our approach results in a strategy that is profitable, robust, and risk-minimal -- outperforming the traditional ensemble strategy as well as single agent algorithms and market metrics. Our findings determine that the conventional practice of switching ensemble agents every fixed-number of months is sub-optimal, and that a dynamic sentiment-based framework greatly unlocks additional performance within these agents. Furthermore, as we have designed our algorithm with simplicity and efficiency in mind, we hypothesize that the transition of our method from historical evaluation towards real-time trading with live data should be relatively simple.

In recent years, there has been a lot of research work activity focused on carrying out asymptotic and non-asymptotic convergence analyses for two-timescale actor critic algorithms where the actor updates are performed on a timescale that is slower than that of the critic. In a recent work, the critic-actor algorithm has been presented for the infinite horizon discounted cost setting in the look-up table case where the timescales of the actor and the critic are reversed and asymptotic convergence analysis has been presented. In our work, we present the first critic-actor algorithm with function approximation and in the long-run average reward setting and present the first finite-time (non-asymptotic) analysis of such a scheme. We obtain optimal learning rates and prove that our algorithm achieves a sample complexity of $\mathcal{\tilde{O}}(\epsilon^{-2.08})$ for the mean squared error of the critic to be upper bounded by $\epsilon$ which is better than the one obtained for actor-critic in a similar setting. We also show the results of numerical experiments on three benchmark settings and observe that the critic-actor algorithm competes well with the actor-critic algorithm.

In reinforcement learning (RL), different rewards can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach to using rewards for learning. We introduce max-reward RL, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic and stochastic environments and can be easily combined with state-of-the-art RL algorithms. In the experiments, we study the performance of max-reward RL algorithms in two goal-reaching environments from Gymnasium-Robotics and demonstrate its benefits over standard RL. The code is publicly available.

We consider the problem of efficiently routing jobs that arrive into a central queue to a system of heterogeneous servers. Unlike homogeneous systems, a threshold policy, that routes jobs to the slow server(s) when the queue length exceeds a certain threshold, is known to be optimal for the one-fast-one-slow two-server system. But an optimal policy for the multi-server system is unknown and non-trivial to find. While Reinforcement Learning (RL) has been recognized to have great potential for learning policies in such cases, our problem has an exponentially large state space size, rendering standard RL inefficient. In this work, we propose ACHQ, an efficient policy gradient based algorithm with a low dimensional soft threshold policy parameterization that leverages the underlying queueing structure. We provide stationary-point convergence guarantees for the general case and despite the low-dimensional parameterization prove that ACHQ converges to an approximate global optimum for the special case of two servers. Simulations demonstrate an improvement in expected response time of up to ~30% over the greedy policy that routes to the fastest available server.

The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with minimal deviation from the initial policy. While considered as a straightforward solution, reinforcement learning (RL) suffers from high variance in policy updates, which impedes efficient policy improvement. Recently, direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. Though simple to implement, DPO is derived based on the optimal policy that is not assured to be achieved in practice, which undermines its convergence to the intended solution. In this paper, we propose efficient exact optimization (EXO) of the alignment objective. We prove that EXO is guaranteed to optimize in the same direction as the RL algorithms asymptotically for arbitary parametrization of the policy, while enables efficient optimization by circumventing the complexities associated with RL algorithms. We compare our method to DPO with both theoretical and empirical analyses, and further demonstrate the advantages of our method over existing approaches on realistic human preference data.

We study a primal-dual reinforcement learning (RL) algorithm for the online constrained Markov decision processes (CMDP) problem, wherein the agent explores an optimal policy that maximizes return while satisfying constraints. Despite its widespread practical use, the existing theoretical literature on primal-dual RL algorithms for this problem only provides sublinear regret guarantees and fails to ensure convergence to optimal policies. In this paper, we introduce a novel policy gradient primal-dual algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and polynomial sample complexity for any target accuracy. Notably, this represents the first Uniform-PAC algorithm for the online CMDP problem. In addition to the theoretical guarantees, we empirically demonstrate in a simple CMDP that our algorithm converges to optimal policies, while an existing algorithm exhibits oscillatory performance and constraint violation.

Offline reinforcement learning (RL) algorithms can improve the decision making via stitching sub-optimal trajectories to obtain more optimal ones. This capability is a crucial factor in enabling RL to learn policies that are superior to the behavioral policy. On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance. In order to endow stitching capability to DT, we abstract trajectory stitching as expert matching and introduce our approach, ContextFormer, which integrates contextual information-based imitation learning (IL) and sequence modeling to stitch sub-optimal trajectory fragments by emulating the representations of a limited number of expert trajectories. To validate our claim, we conduct experiments from two perspectives: 1) We conduct extensive experiments on D4RL benchmarks under the settings of IL, and experimental results demonstrate ContextFormer can achieve competitive performance in multi-IL settings. 2) More importantly, we conduct a comparison of ContextFormer with diverse competitive DT variants using identical training datasets. The experimental results unveiled ContextFormer's superiority, as it outperformed all other variants, showcasing its remarkable performance.

Diffusion planning has been recognized as an effective decision-making paradigm in various domains. The capability of conditionally generating high-quality long-horizon trajectories makes it a promising research direction. However, existing diffusion planning methods suffer from low decision-making frequencies due to the expensive iterative sampling cost. To address this issue, we introduce DiffuserLite, a super fast and lightweight diffusion planning framework. DiffuserLite employs a planning refinement process (PRP) to generate coarse-to-fine-grained trajectories, significantly reducing the modeling of redundant information and leading to notable increases in decision-making frequency. Our experimental results demonstrate that DiffuserLite achieves a decision-making frequency of $122$Hz ($112.7$x faster than previous mainstream frameworks) and reaches state-of-the-art performance on D4RL benchmarks. In addition, our neat DiffuserLite framework can serve as a flexible plugin to enhance decision frequency in other diffusion planning algorithms, providing a structural design reference for future works. More details and visualizations are available at https://diffuserlite.github.io/.