Wee Sun Lee

Yong Liang Goh, Zhiguang Cao, Yining Ma et al.

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on entirely random problem instances that inadequately capture real-world scenarios. In this paper, we introduce realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and derive the following insights: (1) The optimal next node (or city) to visit often lies within proximity to the current node, suggesting the potential benefits of biasing choices based on current locations. (2) Effectively solving the TSP requires robust tracking of unvisited nodes and warrants succinct grouping strategies. Building upon these insights, we propose integrating a learnable choice layer inspired by Hypernetworks to prioritize choices based on the current location, and a learnable approximate clustering algorithm inspired by the Expectation-Maximization algorithm to facilitate grouping the unvisited cities. Together, these two contributions form a hierarchical approach towards solving the realistic TSP by considering both immediate local neighbourhoods and learning an intermediate set of node representations. Our hierarchical approach yields superior performance compared to both classical and recent transformer models, showcasing the efficacy of the key designs.

Zirui Zhao, Boye Niu, David Hsu et al.

We study abstract visual composition, in which identity is primarily determined by the spatial configuration and relations among a small set of geometric primitives (e.g., parts, symmetry, topology). They are invariant primarily to texture and photorealistic detail. Composing such structures from fixed components under geometric constraints and vague goal specification (such as text) is non-trivial due to combinatorial placement choices, limited data, and discrete feasibility (overlap-free, allowable orientations), which create a sparse solution manifold ill-suited to purely statistical pixel-space generators. We propose a constraint-guided framework that combines explicit geometric reasoning with neural semantics. An AlphaGo-style search enforces feasibility, while a fine-tuned vision-language model scores semantic alignment as reward signals. Our algorithm uses a policy network as a heuristic in Monte-Carlo Tree Search and fine-tunes the network via search-generated plans. Inspired by the Generative Adversarial Network, we use the generated instances for adversarial reward refinement. Over time, the generation should approach the actual data more closely when the reward model cannot distinguish between generated instances and ground-truth. In the Tangram Assembly task, our approach yields higher validity and semantic fidelity than diffusion and auto-regressive baselines, especially as constraints tighten.

Xiao Ma, Siwei Chen, David Hsu et al.

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the commonly used generative observation model often does, and is significantly more robust. CVRL achieves comparable performance with state-of-the-art model-based DRL methods on standard Mujoco tasks. It significantly outperforms them on Natural Mujoco tasks and a robot box-pushing task with complex observations, e.g., dynamic shadows. The CVRL code is available publicly at https://github.com/Yusufma03/CVRL.

Liwei Kang, Wee Sun Lee

Continual learning, an important aspect of artificial intelligence and machine learning research, focuses on developing models that learn and adapt to new tasks while retaining previously acquired knowledge. Existing continual learning algorithms usually involve a small number of tasks with uniform sizes and may not accurately represent real-world learning scenarios. In this paper, we investigate the performance of continual learning algorithms with a large number of tasks drawn from a task distribution that is long-tail in terms of task sizes. We design one synthetic dataset and two real-world continual learning datasets to evaluate the performance of existing algorithms in such a setting. Moreover, we study an overlooked factor in continual learning, the optimizer states, e.g. first and second moments in the Adam optimizer, and investigate how it can be used to improve continual learning performance. We propose a method that reuses the optimizer states in Adam by maintaining a weighted average of the second moments from previous tasks. We demonstrate that our method, compatible with most existing continual learning algorithms, effectively reduces forgetting with only a small amount of additional computational or memory costs, and provides further improvements on existing continual learning algorithms, particularly in a long-tail task sequence.

Dixant Mittal, Wee Sun Lee

In decision-making problems with limited training data, policy functions approximated using deep neural networks often exhibit suboptimal performance. An alternative approach involves learning a world model from the limited data and determining actions through online search. However, the performance is adversely affected by compounding errors arising from inaccuracies in the learned world model. While methods like TreeQN have attempted to address these inaccuracies by incorporating algorithmic inductive biases into the neural network architectures, the biases they introduce are often weak and insufficient for complex decision-making tasks. In this work, we introduce Differentiable Tree Search Network (D-TSN), a novel neural network architecture that significantly strengthens the inductive bias by embedding the algorithmic structure of a best-first online search algorithm. D-TSN employs a learned world model to conduct a fully differentiable online search. The world model is jointly optimized with the search algorithm, enabling the learning of a robust world model and mitigating the effect of prediction inaccuracies. Further, we note that a naive incorporation of best-first search could lead to a discontinuous loss function in the parameter space. We address this issue by adopting a stochastic tree expansion policy, formulating search tree expansion as another decision-making task, and introducing an effective variance reduction technique for the gradient computation. We evaluate D-TSN in an offline-RL setting with a limited training data scenario on Procgen games and grid navigation task, and demonstrate that D-TSN outperforms popular model-free and model-based baselines.

Min Chen, David Hsu, Wee Sun Lee

Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the intention as a latent variable. We then embed the human behavior model into a principled probabilistic decision model, which enables the robot to (i) explore actively in order to infer human intentions and (ii) choose actions that maximize its performance. Furthermore, the robot learns from the demonstrated actions of human experts to further improve exploration. Preliminary experiments in simulation indicate that our approach, when applied to autonomous driving, improves the efficiency and safety of driving in common interactive driving scenarios.

Min Chen, Emilio Frazzoli, David Hsu et al.

The partially observable Markov decision process (POMDP) provides a principled general model for planning under uncertainty. However, solving a general POMDP is computationally intractable in the worst case. This paper introduces POMDP-lite, a subclass of POMDPs in which the hidden state variables are constant or only change deterministically. We show that a POMDP-lite is equivalent to a set of fully observable Markov decision processes indexed by a hidden parameter and is useful for modeling a variety of interesting robotic tasks. We develop a simple model-based Bayesian reinforcement learning algorithm to solve POMDP-lite models. The algorithm performs well on large-scale POMDP-lite models with up to $10^{20}$ states and outperforms the state-of-the-art general-purpose POMDP algorithms. We further show that the algorithm is near-Bayesian-optimal under suitable conditions.

Yi Wang, Kok Sung Won, David Hsu et al.

Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them. This paper presents Monte Carlo BRL (MC-BRL), a simple and general approach to BRL. MC-BRL samples a priori a finite set of hypotheses for the model parameter values and forms a discrete partially observable Markov decision process (POMDP) whose state space is a cross product of the state space for the reinforcement learning task and the sampled model parameter space. The POMDP does not require conjugate distributions for belief representation, as earlier works do, and can be solved relatively easily with point-based approximation algorithms. MC-BRL naturally handles both fully and partially observable worlds. Theoretical and experimental results show that the discrete POMDP approximates the underlying BRL task well with guaranteed performance.