Transfer reinforcement learning aims to derive a near-optimal policy for a target environment with limited data by leveraging abundant data from related source domains. However, it faces two key challenges: the lack of performance guarantees for the transferred policy, which can lead to undesired actions, and the risk of negative transfer when multiple source domains are involved. We propose a novel framework based on the pessimism principle, which constructs and optimizes a conservative estimation of the target domain's performance. Our framework effectively addresses the two challenges by providing an optimized lower bound on target performance, ensuring safe and reliable decisions, and by exhibiting monotonic improvement with respect to the quality of the source domains, thereby avoiding negative transfer. We construct two types of conservative estimations, rigorously characterize their effectiveness, and develop efficient distributed algorithms with convergence guarantees. Our framework provides a theoretically sound and practically robust solution for transfer learning in reinforcement learning.
Sixth generation (6G) wireless technology is anticipated to introduce Integrated Sensing and Communication (ISAC) as a transformative paradigm. ISAC unifies wireless communication and RADAR or other forms of sensing to optimize spectral and hardware resources. This paper presents a pioneering framework that leverages ISAC sensing data to enhance beam selection processes in complex indoor environments. By integrating multi-modal transformer models with a multi-agent contextual bandit algorithm, our approach utilizes ISAC sensing data to improve communication performance and achieves high spectral efficiency (SE). Specifically, the multi-modal transformer can capture inter-modal relationships, enhancing model generalization across diverse scenarios. Experimental evaluations on the DeepSense 6G dataset demonstrate that our model outperforms traditional deep reinforcement learning (DRL) methods, achieving superior beam prediction accuracy and adaptability. In the single-user scenario, we achieve an average SE regret improvement of 49.6% as compared to DRL. Furthermore, we employ transfer reinforcement learning to reduce training time and improve model performance in multi-user environments. In the multi-user scenario, this approach enhances the average SE regret, which is a measure to demonstrate how far the learned policy is from the optimal SE policy, by 19.7% compared to training from scratch, even when the latter is trained 100 times longer.
Online Reinforcement learning (RL) typically requires high-stakes online interaction data to learn a policy for a target task. This prompts interest in leveraging historical data to improve sample efficiency. The historical data may come from outdated or related source environments with different dynamics. It remains unclear how to effectively use such data in the target task to provably enhance learning and sample efficiency. To address this, we propose a hybrid transfer RL (HTRL) setting, where an agent learns in a target environment while accessing offline data from a source environment with shifted dynamics. We show that -- without information on the dynamics shift -- general shifted-dynamics data, even with subtle shifts, does not reduce sample complexity in the target environment. However, with prior information on the degree of the dynamics shift, we design HySRL, a transfer algorithm that achieves problem-dependent sample complexity and outperforms pure online RL. Finally, our experimental results demonstrate that HySRL surpasses state-of-the-art online RL baseline.
Many reinforcement learning (RL) algorithms are too costly to use in practice due to the large sizes $S, A$ of the problem's state and action space. To resolve this issue, we study transfer RL with latent low rank structure. We consider the problem of transferring a latent low rank representation when the source and target MDPs have transition kernels with Tucker rank $(S , d, A )$, $(S , S , d), (d, S, A )$, or $(d , d , d )$. In each setting, we introduce the transfer-ability coefficient $\alpha$ that measures the difficulty of representational transfer. Our algorithm learns latent representations in each source MDP and then exploits the linear structure to remove the dependence on $S, A $, or $S A$ in the target MDP regret bound. We complement our positive results with information theoretic lower bounds that show our algorithms (excluding the ($d, d, d$) setting) are minimax-optimal with respect to $\alpha$.
In this paper, we consider a transfer reinforcement learning problem involving agents with different action spaces. Specifically, for any new unseen task, the goal is to use a successful demonstration of this task by an expert agent in its action space to enable a learner agent learn an optimal policy in its own different action space with fewer samples than those required if the learner was learning on its own. Existing transfer learning methods across different action spaces either require handcrafted mappings between those action spaces provided by human experts, which can induce bias in the learning procedure, or require the expert agent to share its policy parameters with the learner agent, which does not generalize well to unseen tasks. In this work, we propose a method that learns a subgoal mapping between the expert agent policy and the learner agent policy. Since the expert agent and the learner agent have different action spaces, their optimal policies can have different subgoal trajectories. We learn this subgoal mapping by training a Long Short Term Memory (LSTM) network for a distribution of tasks and then use this mapping to predict the learner subgoal sequence for unseen tasks, thereby improving the speed of learning by biasing the agent's policy towards the predicted learner subgoal sequence. Through numerical experiments, we demonstrate that the proposed learning scheme can effectively find the subgoal mapping underlying the given distribution of tasks. Moreover, letting the learner agent imitate the expert agent's policy with the learnt subgoal mapping can significantly improve the sample efficiency and training time of the learner agent in unseen new tasks.
Reconfigurable intelligent surface (RIS) becomes a promising technique for 6G networks by reshaping signal propagation in smart radio environments. However, it also leads to significant complexity for network management due to the large number of elements and dedicated phase-shift optimization. In this work, we provide an overview of machine learning (ML)-enabled optimization for RIS-aided 6G networks. In particular, we focus on various reinforcement learning (RL) techniques, e.g., deep Q-learning, multi-agent reinforcement learning, transfer reinforcement learning, hierarchical reinforcement learning, and offline reinforcement learning. Different from existing studies, this work further discusses how large language models (LLMs) can be combined with RL to handle network optimization problems. It shows that LLM offers new opportunities to enhance the capabilities of RL algorithms in terms of generalization, reward function design, multi-modal information processing, etc. Finally, we identify the future challenges and directions of ML-enabled optimization for RIS-aided 6G networks.
This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition dynamics. In this setting, the Q-function of each RL problem (task) can be decomposed into a successor feature (SF) and a reward mapping: the former characterizes the transition dynamics, and the latter characterizes the task-specific reward function. This Q-function decomposition, coupled with a policy improvement operator known as generalized policy improvement (GPI), reduces the sample complexity of finding the optimal Q-function, and thus the SF \& GPI framework exhibits promising empirical performance compared to traditional RL methods like Q-learning. However, its theoretical foundations remain largely unestablished, especially when learning the successor features using deep neural networks (SF-DQN). This paper studies the provable knowledge transfer using SFs-DQN in transfer RL problems. We establish the first convergence analysis with provable generalization guarantees for SF-DQN with GPI. The theory reveals that SF-DQN with GPI outperforms conventional RL approaches, such as deep Q-network, in terms of both faster convergence rate and better generalization. Numerical experiments on real and synthetic RL tasks support the superior performance of SF-DQN \& GPI, aligning with our theoretical findings.
Multi-Agent Reinforcement Learning (MARL) algorithms are widely adopted in tackling complex tasks that require collaboration and competition among agents in dynamic Multi-Agent Systems (MAS). However, learning such tasks from scratch is arduous and may not always be feasible, particularly for MASs with a large number of interactive agents due to the extensive sample complexity. Therefore, reusing knowledge gained from past experiences or other agents could efficiently accelerate the learning process and upscale MARL algorithms. In this study, we introduce a novel framework that enables transfer learning for MARL through unifying various state spaces into fixed-size inputs that allow one unified deep-learning policy viable in different scenarios within a MAS. We evaluated our approach in a range of scenarios within the StarCraft Multi-Agent Challenge (SMAC) environment, and the findings show significant enhancements in multi-agent learning performance using maneuvering skills learned from other scenarios compared to agents learning from scratch. Furthermore, we adopted Curriculum Transfer Learning (CTL), enabling our deep learning policy to progressively acquire knowledge and skills across pre-designed homogeneous learning scenarios organized by difficulty levels. This process promotes inter- and intra-agent knowledge transfer, leading to high multi-agent learning performance in more complicated heterogeneous scenarios.
We propose Value Explicit Pretraining (VEP), a method that learns generalizable representations for transfer reinforcement learning. VEP enables learning of new tasks that share similar objectives as previously learned tasks, by learning an encoder for objective-conditioned representations, irrespective of appearance changes and environment dynamics. To pre-train the encoder from a sequence of observations, we use a self-supervised contrastive loss that results in learning temporally smooth representations. VEP learns to relate states across different tasks based on the Bellman return estimate that is reflective of task progress. Experiments using a realistic navigation simulator and Atari benchmark show that the pretrained encoder produced by our method outperforms current SoTA pretraining methods on the ability to generalize to unseen tasks. VEP achieves up to a 2 times improvement in rewards on Atari and visual navigation, and up to a 3 times improvement in sample efficiency. For videos of policy performance visit our https://sites.google.com/view/value-explicit-pretraining/
In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a transferring approach with a parameter-compositional formulation. We investigate ways to improve the training of multi-task reinforcement learning which serves as the foundation for transferring. Then we conduct a number of transferring experiments on various manipulation tasks. Experimental results demonstrate that the proposed approach can have improved performance in the multi-task training stage, and further show effective transferring in terms of both sample efficiency and performance.
In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)} problem. First, we formulate MTRL for discrete MDPs and Linear Quadratic Regulators (LQRs) with continuous state actions. Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings. In the first stage, MLEMTRL uses a \textit{constrained Maximum Likelihood Estimation (MLE)}-based approach to estimate the target MDP model using a set of known MDP models. In the second stage, using the estimated target MDP model, MLEMTRL deploys a model-based planning algorithm appropriate for the MDP class. Theoretically, we prove worst-case regret bounds for MLEMTRL both in realisable and non-realisable settings. We empirically demonstrate that MLEMTRL allows faster learning in new MDPs than learning from scratch and achieves near-optimal performance depending on the similarity of the available MDPs and the target MDP.
We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to go to a specific room in a building using observations from its own camera, while having access to the floor plan. We formalize this setting as transfer reinforcement learning from an abstract simulator, which we assume is deterministic (such as a simple model of moving around the floor plan), but which is only required to capture the target domain's latent-state dynamics approximately up to unknown (bounded) perturbations (to account for environment stochasticity). Crucially, we assume no prior knowledge about the structure of observations in the target domain except that they can be used to identify the latent states (but the decoding map is unknown). Under these assumptions, we present an algorithm, called TASID, that learns a robust policy in the target domain, with sample complexity that is polynomial in the horizon, and independent of the number of states, which is not possible without access to some prior knowledge. In synthetic experiments, we verify various properties of our algorithm and show that it empirically outperforms transfer RL algorithms that require access to "full simulators" (i.e., those that also simulate observations).
Transfer learning approaches in reinforcement learning aim to assist agents in learning their target domains by leveraging the knowledge learned from other agents that have been trained on similar source domains. For example, recent research focus within this space has been placed on knowledge transfer between tasks that have different transition dynamics and reward functions; however, little focus has been placed on knowledge transfer between tasks that have different action spaces. In this paper, we approach the task of transfer learning between domains that differ in action spaces. We present a reward shaping method based on source embedding similarity that is applicable to domains with both discrete and continuous action spaces. The efficacy of our approach is evaluated on transfer to restricted action spaces in the Acrobot-v1 and Pendulum-v0 domains. A comparison with two baselines shows that our method does not outperform these baselines in these continuous action spaces but does show an improvement in these discrete action spaces. We conclude our analysis with future directions for this work.
Network slicing is a critical technique for 5G communications that covers radio access network (RAN), edge, transport and core slicing.The evolving network architecture requires the orchestration of multiple network resources such as radio and cache resources. In recent years, machine learning (ML) techniques have been widely applied for network management. However, most existing works do not take advantage of the knowledge transfer capability in ML. In this paper, we propose a deep transfer reinforcement learning (DTRL) scheme for joint radio and cache resource allocation to serve 5G RAN slicing. We first define a hierarchical architecture for joint resource allocation. Then we propose two DTRL algorithms: Q-value-based deep transfer reinforcement learning (QDTRL) and action selection-based deep transfer reinforcement learning (ADTRL). In the proposed schemes, learner agents utilize expert agents' knowledge to improve their performance on current tasks. The proposed algorithms are compared with both the model-free exploration bonus deep Q-learning (EB-DQN) and the model-based priority proportional fairness and time-to-live (PPF-TTL) algorithms. Compared with EB-DQN, our proposed DTRL-based method presents 21.4% lower delay for Ultra Reliable Low Latency Communications (URLLC) slice and 22.4% higher throughput for enhanced Mobile Broad Band (eMBB) slice, while achieving significantly faster convergence than EB-DQN. Moreover, 40.8% lower URLLC delay and 59.8% higher eMBB throughput are observed with respect to PPF-TTL.
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \textit{AdaRL}, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across domains are, and furthermore inform us with a minimal set of changes that one has to consider for the purpose of policy adaptation. We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided. We illustrate the efficacy of AdaRL through a series of experiments that vary factors in the observation, transition, and reward functions for Cartpole and Atari games.
In this paper, we consider a transfer Reinforcement Learning (RL) problem in continuous state and action spaces, under unobserved contextual information. For example, the context can represent the mental view of the world that an expert agent has formed through past interactions with this world. We assume that this context is not accessible to a learner agent who can only observe the expert data. Then, our goal is to use the context-aware expert data to learn an optimal context-unaware policy for the learner using only a few new data samples. Such problems are typically solved using imitation learning that assumes that both the expert and learner agents have access to the same information. However, if the learner does not know the expert context, using the expert data alone will result in a biased learner policy and will require many new data samples to improve. To address this challenge, in this paper, we formulate the learning problem as a causal bound-constrained Multi-Armed-Bandit (MAB) problem. The arms of this MAB correspond to a set of basis policy functions that can be initialized in an unsupervised way using the expert data and represent the different expert behaviors affected by the unobserved context. On the other hand, the MAB constraints correspond to causal bounds on the accumulated rewards of these basis policy functions that we also compute from the expert data. The solution to this MAB allows the learner agent to select the best basis policy and improve it online. And the use of causal bounds reduces the exploration variance and, therefore, improves the learning rate. We provide numerical experiments on an autonomous driving example that show that our proposed transfer RL method improves the learner's policy faster compared to existing imitation learning methods and enjoys much lower variance during training.
The idea of transfer in reinforcement learning (TRL) is intriguing: being able to transfer knowledge from one problem to another problem without learning everything from scratch. This promises quicker learning and learning more complex methods. To gain an insight into the field and to detect emerging trends, we performed a database search. We note a surprisingly late adoption of deep learning that starts in 2018. The introduction of deep learning has not yet solved the greatest challenge of TRL: generalization. Transfer between different domains works well when domains have strong similarities (e.g. MountainCar to Cartpole), and most TRL publications focus on different tasks within the same domain that have few differences. Most TRL applications we encountered compare their improvements against self-defined baselines, and the field is still missing unified benchmarks. We consider this to be a disappointing situation. For the future, we note that: (1) A clear measure of task similarity is needed. (2) Generalization needs to improve. Promising approaches merge deep learning with planning via MCTS or introduce memory through LSTMs. (3) The lack of benchmarking tools will be remedied to enable meaningful comparison and measure progress. Already Alchemy and Meta-World are emerging as interesting benchmark suites. We note that another development, the increase in procedural content generation (PCG), can improve both benchmarking and generalization in TRL.
Traffic congestion is a major challenge in modern urban settings. The industry-wide development of autonomous and automated vehicles (AVs) motivates the question of how can AVs contribute to congestion reduction. Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs executing a controlled multiagent driving policy can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent driving policies for AVs in scenarios with greater complexity. We start by showing that a congestion metric used by past research is manipulable in open road network scenarios where vehicles dynamically join and leave the road. We then propose using a different metric that is robust to manipulation and reflects open network traffic efficiency. Next, we propose a modular transfer reinforcement learning approach, and use it to scale up a multiagent driving policy to outperform human-like traffic and existing approaches in a simulated realistic scenario, which is an order of magnitude larger than past scenarios (hundreds instead of tens of vehicles). Additionally, our modular transfer learning approach saves up to 80% of the training time in our experiments, by focusing its data collection on key locations in the network. Finally, we show for the first time a distributed multiagent policy that improves congestion over human-driven traffic. The distributed approach is more realistic and practical, as it relies solely on existing sensing and actuation capabilities, and does not require adding new communication infrastructure.
Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage. The cross-domain consistency of LUSR allows the policy acquired from the source domain to generalize to other target domains without extra training. We first demonstrate our approach in variants of CarRacing games with customized manipulations, and then verify it in CARLA, an autonomous driving simulator with more complex and realistic visual observations. Our results show that this approach can achieve state-of-the-art domain adaptation performance in related RL tasks and outperforms prior approaches based on latent-representation based RL and image-to-image translation.
In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide learning. However, acquiring expert demonstrations can be expensive. This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks. The action prior is a probability distribution over actions that summarizes the set of policies found solving previous tasks. Our results indicate that this approach can be used to solve robotic manipulation problems that would otherwise be infeasible without expert demonstrations. Source code is available at \url{https://github.com/ondrejba/action_priors}.