Reinforcement Learning (RL) is crucial for data-driven decision-making but suffers from sample inefficiency. This poses a risk to system safety and can be costly in real-world environments with physical interactions. This paper proposes a human-inspired framework to improve the sample efficiency of RL algorithms, which gradually provides the learning agent with simpler but similar tasks that progress toward the main task. The proposed method does not require pre-training and can be applied to any goal, environment, and RL algorithm, including value-based and policy-based methods, as well as tabular and deep-RL methods. The framework is evaluated on a Random Walk and optimal control problem with constraint, showing good performance in improving the sample efficiency of RL-learning algorithms.

Despite the huge success of reinforcement learning (RL) in solving many difficult problems, its Achilles heel has always been sample inefficiency. On the other hand, in RL, taking advantage of prior knowledge, intentionally or unintentionally, has usually been avoided, so that, training an agent from scratch is common. This not only causes sample inefficiency but also endangers safety –especially during exploration. In this paper, we help the agent learn from the environment by using the pre-existing (but not necessarily exact or complete) solution for a task. Our proposed method can be integrated with any RL algorithm developed based on policy gradient and actor-critic methods. The results on five tasks with different difficulty levels by using two well-known actor-critic-based methods as the backbone of our proposed method (SAC and TD3) show our success in greatly improving sample efficiency and final performance. We have gained these results alongside robustness to noisy environments at the cost of just a slight computational overhead, which is negligible.

Parallel stochastic gradient methods are gaining prominence in solving large-scale machine learning problems that involve data distributed across multiple nodes. However, obtaining unbiased stochastic gradients, which have been the focus of most theoretical research, is challenging in many distributed machine learning applications. The gradient estimations easily become biased, for example, when gradients are compressed or clipped, when data is shuffled, and in meta-learning and reinforcement learning. In this work, we establish worst-case bounds on parallel momentum methods under biased gradient estimation on both general non-convex and μ-PL non-convex problems. Our analysis covers general distributed optimization problems, and we work out the implications for special cases where gradient estimates are biased, i.e. in meta-learning and when the gradients are compressed or clipped. Our numerical experiments verify our theoretical findings and show faster convergence performance of momentum methods than traditional biased gradient descent.

Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collaboratively learn a single policy by aggregating local estimations. However, this aggregation step incurs significant communication costs. In this paper, we propose CompFedRL, a communication-efficient FedRL approach incorporating both \textit{periodic aggregation} and (direct/error-feedback) compression mechanisms. Specifically, we consider compressed federated Q-learning with a generative model setup, where a central server learns an optimal Q-function by periodically aggregating compressed Q-estimates from local agents. For the first time, we characterize the impact of these two mechanisms (which have remained elusive) by providing a finite-time analysis of our algorithm, demonstrating strong convergence behaviors when utilizing either direct or error-feedback compression. Our bounds indicate improved solution accuracy concerning the number of agents and other federated hyperparameters while simultaneously reducing communication costs. To corroborate our theory, we also conduct in-depth numerical experiments to verify our findings, considering Top-K and Sparsified-K sparsification operators.

Data similarity assumptions have traditionally been relied upon to understand the convergence behaviors of federated learning methods. Unfortunately, this approach often demands fine-tuning step sizes based on the level of data similarity. When data similarity is low, these small step sizes result in an unacceptably slow convergence speed for federated methods. In this paper, we present a novel and unified framework for analyzing the convergence of federated learning algorithms without the need for data similarity conditions. Our analysis centers on an inequality that captures the influence of step sizes on algorithmic convergence performance. By applying our theorems to well-known federated algorithms, we derive precise expressions for three widely used step size schedules: fixed, diminishing, and step-decay step sizes, which are independent of data similarity conditions. Finally, we conduct comprehensive evaluations of the performance of these federated learning algorithms, employing the proposed step size strategies to train deep neural network models on benchmark datasets under varying data similarity conditions. Our findings demonstrate significant improvements in convergence speed and overall performance, marking a substantial advancement in federated learning research.

Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedRL algorithms assume that all agents operate in identical environments, which is often unrealistic. In real-world applications, such as multi-robot teams, crowdsourced systems, and large-scale sensor networks, each agent may experience slightly different transition dynamics, leading to inherent model mismatches. In this paper, we first establish linear convergence guarantees for single-agent temporal difference learning (TD(0)) in policy evaluation and demonstrate that under a perturbed environment, the agent suffers a systematic bias that prevents accurate estimation of the true value function. This result holds under both i.i.d. and Markovian sampling regimes. We then extend our analysis to the federated TD(0) (FedTD(0)) setting, where multiple agents, each interacting with its own perturbed environment, periodically share value estimates to collaboratively approximate the true value function of a common underlying model. Our theoretical results indicate the impact of model mismatch, network connectivity, and mixing behavior on the convergence of FedTD(0). Empirical experiments corroborate our theoretical gains, highlighting that even moderate levels of information sharing significantly mitigate environment-specific errors.