Sang-Hyun Lee

Sang-Hyun Lee, Yoonjae Jung, Seung-Woo Seo

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structure. Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies. The high-level policy selects which low-level policy to activate at a lower frequency and the activated low-level policy selects an action at each time step. Recent HRL algorithms have achieved performance gains over standard RL algorithms in synthetic navigation tasks. However, we cannot apply these HRL algorithms to real-world navigation tasks. One of the main challenges is that real-world navigation tasks require an agent to perform safe and interactive behaviors in dynamic environments. In this paper, we propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL to enable an agent to learn safe and interactive behaviors in real-world navigation tasks. Imagination is to predict the consequences of actions without interactions with actual environments. The key idea behind IAHRL is that the low-level policies imagine safe and structured behaviors, and then the high-level policy infers interactions with surrounding objects by interpreting the imagined behaviors. We also introduce a new attention mechanism that allows our high-level policy to be permutation-invariant to the order of surrounding objects and to prioritize our agent over them. To evaluate IAHRL, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.

Sang-Hyun Lee, Seung-Woo Seo

A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation and manipulation tasks, outperforming baselines with significantly fewer manual resets.

Jinwoo Choi, Sang-Hyun Lee, Seung-Woo Seo

Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and generate only a single intermediate subgoal, making them inadequate for complex tasks that require coordinating multiple intermediate decisions. To address this limitation, we draw inspiration from the chain-of-thought paradigm and propose the Chain-of-Goals Hierarchical Policy (CoGHP), a novel framework that reformulates hierarchical decision-making as autoregressive sequence modeling within a unified architecture. Given a state and a final goal, CoGHP autoregressively generates a sequence of latent subgoals followed by the primitive action, where each latent subgoal acts as a reasoning step that conditions subsequent predictions. To implement this efficiently, we pioneer the use of an MLP-Mixer backbone, which supports cross-token communication and captures structural relationships among state, goal, latent subgoals, and action. Across challenging navigation and manipulation benchmarks, CoGHP consistently outperforms strong offline baselines, demonstrating improved performance on long-horizon tasks.

Wongi Park, Jordan A. James, Myeongseok Nam et al.

We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained dense image collections to enhance 3D representation in real-world scenarios, our method not only effectively tackles sparse unconstrained image collections, but also shows high-quality 3D rendering results. To do this, we introduce reference-guided view refinement with a diffusion model using a transient mask and a reference image to enhance the 3D representation and mitigate artifacts in rendered views. Furthermore, we address sparse regions in the Gaussian field via pseudo-view generation along with a sparsity-aware Gaussian replication strategy to amplify Gaussians in the sparse regions. Extensive experiments on publicly available datasets demonstrate that our methodology consistently outperforms existing methods (e.g., PSNR - 17.2%, SSIM - 10.8%, LPIPS - 4.0%) and provides high-fidelity 3D rendering results. This advancement paves the way for realizing unconstrained real-world scenarios without labor-intensive data acquisition. Our project page is available at $\href{https://robotic-vision-lab.github.io/SaveWildGS/}{here}$

Sang-Hyun Lee, Daehyeok Kwon, Seung-Woo Seo

Recent reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. However, autonomous vehicles trained in simulation often struggle to work well in the real world due to the fidelity gap between simulated and real-world environments. While directly training real-world autonomous vehicles with RL algorithms is a promising approach to bypass the fidelity gap problem, it presents several challenges. One critical yet often overlooked challenge is the need to reset a driving environment between every episode. This reset process demands significant human intervention, leading to poor training efficiency in the real world. In this paper, we introduce a novel autonomous algorithm that enables off-the-shelf RL algorithms to train autonomous vehicles with minimal human intervention. Our algorithm reduces unnecessary human intervention by aborting episodes to prevent unsafe states and identifying informative initial states for subsequent episodes. The key idea behind identifying informative initial states is to estimate the expected amount of information that can be obtained from under-explored but reachable states. Our algorithm also revisits rule-based autonomous driving algorithms and highlights their benefits in safely returning an autonomous vehicle to initial states. To evaluate how much human intervention is required during training, we implement challenging urban driving tasks that require an autonomous vehicle to reset to initial states on its own. The experimental results show that our autonomous algorithm is task-agnostic and achieves competitive driving performance with much less human intervention than baselines.