In this paper, we propose and study opportunistic reinforcement learning - a new variant of reinforcement learning problems where the regret of selecting a suboptimal action varies under an external environmental condition known as the variation factor. When the variation factor is low, so is the regret of selecting a suboptimal action and vice versa. Our intuition is to exploit more when the variation factor is high, and explore more when the variation factor is low. We demonstrate the benefit of this novel framework for finite-horizon episodic MDPs by designing and evaluating OppUCRL2 and OppPSRL algorithms. Our algorithms dynamically balance the exploration-exploitation trade-off for reinforcement learning by introducing variation factor-dependent optimism to guide exploration. We establish an $\tilde{O}(HS \sqrt{AT})$ regret bound for the OppUCRL2 algorithm and show through simulations that both OppUCRL2 and OppPSRL algorithm outperform their original corresponding algorithms.

Meticulously analysing the empirical strengths and weaknesses of reinforcement learning methods in hard (challenging) environments is essential to inspire innovations and assess progress in the field. In tabular reinforcement learning, there is no well-established standard selection of environments to conduct such analysis, which is partially due to the lack of a widespread understanding of the rich theory of hardness of environments. The goal of this paper is to unlock the practical usefulness of this theory through four main contributions. First, we present a systematic survey of the theory of hardness, which also identifies promising research directions. Second, we introduce Colosseum, a pioneering package that enables empirical hardness analysis and implements a principled benchmark composed of environments that are diverse with respect to different measures of hardness. Third, we present an empirical analysis that provides new insights into computable measures. Finally, we benchmark five tabular agents in our newly proposed benchmark. While advancing the theoretical understanding of hardness in non-tabular reinforcement learning remains essential, our contributions in the tabular setting are intended as solid steps towards a principled non-tabular benchmark. Accordingly, we benchmark four agents in non-tabular versions of Colosseum environments, obtaining results that demonstrate the generality of tabular hardness measures.

In this paper, we establish the global optimality and convergence rate of an off-policy actor critic algorithm in the tabular setting without using density ratio to correct the discrepancy between the state distribution of the behavior policy and that of the target policy. Our work goes beyond existing works on the optimality of policy gradient methods in that existing works use the exact policy gradient for updating the policy parameters while we use an approximate and stochastic update step. Our update step is not a gradient update because we do not use a density ratio to correct the state distribution, which aligns well with what practitioners do. Our update is approximate because we use a learned critic instead of the true value function. Our update is stochastic because at each step the update is done for only the current state action pair. Moreover, we remove several restrictive assumptions from existing works in our analysis. Central to our work is the finite sample analysis of a generic stochastic approximation algorithm with time-inhomogeneous update operators on time-inhomogeneous Markov chains, based on its uniform contraction properties.

Abstract: Unmanned aerial vehicle (UAV) is steadily growing as a promising technology for next-generation communication systems due to their appealing features such as wide coverage with high altitude, on-demand low-cost deployment, and fast responses. UAV communications are fundamentally different from the conventional terrestrial and satellite communications owing to the high mobility and the unique channel characteristics of air-ground links. However, obtaining effective channel state information (CSI) is challenging because of the dynamic propagation environment and variable transmission delay. In this paper, a deep learning (DL)-based CSI prediction framework is proposed to address channel aging problem by extracting the most discriminative features from the UAV wireless signals. Specifically, we develop a procedure of multiple Gaussian Bernoulli restricted Boltzmann machines (GBRBM) for dimension reduction and pre-training utilization incorporated with an autoencoder-based deep neural networks (DNNs).

Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e.g., part-whole hierarchies, for equivariant vision? and (2) how do we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex action sequences from primitive policies? Our approach exploits hypernetworks, self-supervised learning and reinforcement learning to learn hierarchical world models that combine task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We demonstrate the viability of our approach on a variety of vision datasets (MNIST, FashionMNIST, Omniglot) as well as on a scalable hierarchical planning problem. Our results represent, to our knowledge, the first demonstration of a unified solution to the part-whole learning problem posed by Hinton, the nested reference frames problem posed by Hawkins, and the integrated state-action hierarchy learning problem in reinforcement learning.

Modeling interaction dynamics to generate robot trajectories that enable a robot to adapt and react to a human's actions and intentions is critical for efficient and effective collaborative Human-Robot Interactions (HRI). Learning from Demonstration (LfD) methods from Human-Human Interactions (HHI) have shown promising results, especially when coupled with representation learning techniques. However, such methods for learning HRI either do not scale well to high dimensional data or cannot accurately adapt to changing via-poses of the interacting partner. We propose Multimodal Interactive Latent Dynamics (MILD), a method that couples deep representation learning and probabilistic machine learning to address the problem of two-party physical HRIs. We learn the interaction dynamics from demonstrations, using Hidden Semi-Markov Models (HSMMs) to model the joint distribution of the interacting agents in the latent space of a Variational Autoencoder (VAE). Our experimental evaluations for learning HRI from HHI demonstrations show that MILD effectively captures the multimodality in the latent representations of HRI tasks, allowing us to decode the varying dynamics occurring in such tasks. Compared to related work, MILD generates more accurate trajectories for the controlled agent (robot) when conditioned on the observed agent's (human) trajectory. Notably, MILD can learn directly from camera-based pose estimations to generate trajectories, which we then map to a humanoid robot without the need for any additional training.

Partially Observable Markov Decision Processes (POMDPs) offer a promising world representation for autonomous agents, as they can model both transitional and perceptual uncertainties. Calculating the optimal solution to POMDP problems can be computationally expensive as they require reasoning over the (possibly infinite) space of beliefs. Several approaches have been proposed to overcome this difficulty, such as discretizing the belief space, point-based belief sampling, and Monte Carlo tree search. The Real-Time Dynamic Programming approach of the RTDP-Bel algorithm approximates the value function by storing it in a hashtable with discretized belief keys. We propose an extension to the RTDP-Bel algorithm which we call Belief Branch and Bound RTDP (B$^3$RTDP). Our algorithm uses a bounded value function representation and takes advantage of this in two novel ways: a search-bounding technique based on action selection convergence probabilities, and a method for leveraging early action convergence called the \textit{Convergence Frontier}. Lastly, we empirically demonstrate that B$^3$RTDP can achieve greater returns in less time than the state-of-the-art SARSOP solver on known POMDP problems.

We develop a novel deep learning method for uncertainty quantification in stochastic partial differential equations based on Bayesian neural network (BNN) and Hamiltonian Monte Carlo (HMC). A BNN efficiently learns the posterior distribution of the parameters in deep neural networks by performing Bayesian inference on the network parameters. The posterior distribution is efficiently sampled using HMC to quantify uncertainties in the system. Several numerical examples are shown for both forward and inverse problems in high dimension to demonstrate the effectiveness of the proposed method for uncertainty quantification. These also show promising results that the computational cost is almost independent of the dimension of the problem demonstrating the potential of the method for tackling the so-called curse of dimensionality.

One stream of reinforcement learning research is exploring biologically plausible models and algorithms to simulate biological intelligence and fit neuromorphic hardware. Among them, reward-modulated spike-timing-dependent plasticity (R-STDP) is a recent branch with good potential in energy efficiency. However, current R-STDP methods rely on heuristic designs of local learning rules, thus requiring task-specific expert knowledge. In this paper, we consider a spiking recurrent winner-take-all network, and propose a new R-STDP method, spiking variational policy gradient (SVPG), whose local learning rules are derived from the global policy gradient and thus eliminate the need for heuristic designs. In experiments of MNIST classification and Gym InvertedPendulum, our SVPG achieves good training performance, and also presents better robustness to various kinds of noises than conventional methods.

Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, when agents arbitrarily converge on one out of many equivalent but mutually incompatible policies. Commonly these examples include partial observability, e.g. waving your right hand vs. left hand to convey a covert message. In this paper, we present a novel equivariant network architecture for use in Dec-POMDPs that prevents the agent from learning policies which break symmetries, doing so more effectively than prior methods. Our method also acts as a "coordination-improvement operator" for generic, pre-trained policies, and thus may be applied at test-time in conjunction with any self-play algorithm. We provide theoretical guarantees of our work and test on the AI benchmark task of Hanabi, where we demonstrate our methods outperforming other symmetry-aware baselines in zero-shot coordination, as well as able to improve the coordination ability of a variety of pre-trained policies. In particular, we show our method can be used to improve on the state of the art for zero-shot coordination on the Hanabi benchmark.