Songhwai Oh

Dohyeong Kim, Kyungjae Lee, Songhwai Oh

In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintaining balance. Thus, applying safe reinforcement learning (RL) in such robotic tasks requires to handle multiple constraints and use risk-averse constraints rather than risk-neutral constraints. To this end, we propose a trust region-based safe RL algorithm for multiple constraints called a safe distributional actor-critic (SDAC). Our main contributions are as follows: 1) introducing a gradient integration method to manage infeasibility issues in multi-constrained problems, ensuring theoretical convergence, and 2) developing a TD($λ$) target distribution to estimate risk-averse constraints with low biases. We evaluate SDAC through extensive experiments involving multi- and single-constrained robotic tasks. While maintaining high scores, SDAC shows 1.93 times fewer steps to satisfy all constraints in multi-constrained tasks and 1.78 times fewer constraint violations in single-constrained tasks compared to safe RL baselines. Code is available at: https://github.com/rllab-snu/Safe-Distributional-Actor-Critic.

Dohyeong Kim, Hyeokjin Kwon, Junseok Kim et al.

As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shaping process through intuitive strategies. Initially, instead of a single reward function composed of various terms, we define multiple reward and cost functions within a constrained multi-objective RL (CMORL) framework. For tasks involving sequential complex movements, we segment the task into distinct stages and define multiple rewards and costs for each stage. Finally, we introduce a practical CMORL algorithm that maximizes objectives based on these rewards while satisfying constraints defined by the costs. The proposed method has been successfully demonstrated across a variety of acrobatic tasks in both simulation and real-world environments. Additionally, it has been shown to successfully perform tasks compared to existing RL and constrained RL algorithms. Our code is available at https://github.com/rllab-snu/Stage-Wise-CMORL.

Obin Kwon, Jeongho Park, Songhwai Oh

We propose a novel type of map for visual navigation, a renderable neural radiance map (RNR-Map), which is designed to contain the overall visual information of a 3D environment. The RNR-Map has a grid form and consists of latent codes at each pixel. These latent codes are embedded from image observations, and can be converted to the neural radiance field which enables image rendering given a camera pose. The recorded latent codes implicitly contain visual information about the environment, which makes the RNR-Map visually descriptive. This visual information in RNR-Map can be a useful guideline for visual localization and navigation. We develop localization and navigation frameworks that can effectively utilize the RNR-Map. We evaluate the proposed frameworks on camera tracking, visual localization, and image-goal navigation. Experimental results show that the RNR-Map-based localization framework can find the target location based on a single query image with fast speed and competitive accuracy compared to other baselines. Also, this localization framework is robust to environmental changes, and even finds the most visually similar places when a query image from a different environment is given. The proposed navigation framework outperforms the existing image-goal navigation methods in difficult scenarios, under odometry and actuation noises. The navigation framework shows 65.7% success rate in curved scenarios of the NRNS dataset, which is an improvement of 18.6% over the current state-of-the-art. Project page: https://rllab-snu.github.io/projects/RNR-Map/

Minyoung Hwang, Jaeyeon Jeong, Minsoo Kim et al.

The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algorithms is that if an action is mistaken, the agent fails to follow the instructions or explores unnecessary regions, leading the agent to an irrecoverable path. To tackle this problem, we propose Meta-Explore, a hierarchical navigation method deploying an exploitation policy to correct misled recent actions. We show that an exploitation policy, which moves the agent toward a well-chosen local goal among unvisited but observable states, outperforms a method which moves the agent to a previously visited state. We also highlight the demand for imagining regretful explorations with semantically meaningful clues. The key to our approach is understanding the object placements around the agent in spectral-domain. Specifically, we present a novel visual representation, called scene object spectrum (SOS), which performs category-wise 2D Fourier transform of detected objects. Combining exploitation policy and SOS features, the agent can correct its path by choosing a promising local goal. We evaluate our method in three VLN benchmarks: R2R, SOON, and REVERIE. Meta-Explore outperforms other baselines and shows significant generalization performance. In addition, local goal search using the proposed spectral-domain SOS features significantly improves the success rate by 17.1% and SPL by 20.6% for the SOON benchmark.

Hyeokjin Kwon, Gunmin Lee, Junseo Lee et al.

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations$\unicode{x2013}$reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real$\unicode{x2013}$world Jackal platform. Our proposed framework enhances the performance of algorithms by $39\%$ and reduces constraint violations by $88\%$ on the real-world Jackal platform, demonstrating the framework's efficacy. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

Junseok Kim, Dohyeong Kim, Mineui Hong et al.

Compositional generalization is essential for reaching unseen goals under novel contextual variations in offline goal-conditioned reinforcement learning (GCRL), where a generalist goal-reaching agent must be learned from limited data. Most prior approaches pursue this via trajectory stitching over temporally contiguous segments, which limits composing behaviors across varying contexts. To overcome this limitation, we formalize analogy transduction as synthesizing new plans by composing task-endogenous analogies with given contexts and propose a novel analogy representation tailored for it. Grounded in our theory, this analogy representation captures what changes under optimal task execution, remains invariant to contextual variations, and is sufficient for optimal goal reaching. We further contend that generalization to unseen analogy-context pairs is a practical obstacle in analogy transduction, and introduce a new approach for offline GCRL that enables analogy transduction beyond seen pairs to unseen combinations. We empirically demonstrate the effectiveness of our approach on OGBench manipulation environments, substantially outperforming prior methods that do not perform analogy transduction. Project page: https://rllab-snu.github.io/projects/CTA/

Seunggyu Chang, Jungchan Cho, Songhwai Oh

We propose a dual-domain generative model to estimate a texture map from a single image for colorizing a 3D human model. When estimating a texture map, a single image is insufficient as it reveals only one facet of a 3D object. To provide sufficient information for estimating a complete texture map, the proposed model simultaneously generates multi-view hallucinations in the image domain and an estimated texture map in the texture domain. During the generating process, each domain generator exchanges features to the other by a flow-based local attention mechanism. In this manner, the proposed model can estimate a texture map utilizing abundant multi-view image features from which multiview hallucinations are generated. As a result, the estimated texture map contains consistent colors and patterns over the entire region. Experiments show the superiority of our model for estimating a directly render-able texture map, which is applicable to 3D animation rendering. Furthermore, our model also improves an overall generation quality in the image domain for pose and viewpoint transfer tasks.

Jaewon Lee, Jaeseok Heo, Gunmin Lee et al.

Safe visual navigation is critical for indoor mobile robots operating in cluttered environments. Existing benchmarks, however, often neglect collisions or are designed for outdoor scenarios, making them unsuitable for indoor visual navigation. To address this limitation, we introduce the reactive visual navigation benchmark (RVN-Bench), a collision-aware benchmark for indoor mobile robots. In RVN-Bench, an agent must reach sequential goal positions in previously unseen environments using only visual observations and no prior map, while avoiding collisions. Built on the Habitat 2.0 simulator and leveraging high-fidelity HM3D scenes, RVN-Bench provides large-scale, diverse indoor environments, defines a collision-aware navigation task and evaluation metrics, and offers tools for standardized training and benchmarking. RVN-Bench supports both online and offline learning by offering an environment for online reinforcement learning, a trajectory image dataset generator, and tools for producing negative trajectory image datasets that capture collision events. Experiments show that policies trained on RVN-Bench generalize effectively to unseen environments, demonstrating its value as a standardized benchmark for safe and robust visual navigation. Code and additional materials are available at: https://rvn-bench.github.io/.

Junsung Park, Hogun Kee, Songhwai Oh

This paper presents a modality-augmented fine-tuning framework designed to adapt foundation robot policies to diverse humanoid embodiments. We validate our approach across two distinct settings: (i) the GR1 embodiment, utilizing public datasets where we introduce post-processed modalities, including binary contact signals and ZoeDepth-generated metric depth; and (ii) the Unitree G1 embodiment, for which we contribute a novel multi-modal dataset incorporating cuRobo motion planning, inverse kinematics, and ground-truth contact-force measurements. Our experiments demonstrate that modality augmentation consistently enhances policy performance across different embodiments. Specifically, for the GR1, integrating contact-state cues and RGB-D fusion improves online success rates from 51% to 63%. Furthermore, in the G1 "Pick Apple to Bowl" task, our contact-augmented model achieves a success rate of 94%, significantly outperforming the 48% achieved by standard fine-tuning and the 0% baseline of zero-shot transfer. These results highlight that lightweight post-processing effectively strengthens policies for GR1, while high-quality multi-modal data is crucial for reliable transfer to the Unitree G1. Consequently, this work establishes a unified, data-centric pathway for extending foundation robot policies through targeted modality design and multi-modal fine-tuning.

Hojun Chung, Junseo Lee, Songhwai Oh

Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from compounding errors due to repeated model inference on self-generated states. While geometric horizon models (GHM) alleviate this issue through direct prediction over a discounted infinite-horizon future, they remain challenged in accurately modeling distant future states. To this end, we introduce universal horizon models (UHM), a generalization of GHM that directly predicts future states under arbitrary horizons. Leveraging this flexibility, we propose a scalable value learning method that employs a winsorized horizon distribution to stabilize training by capping excessively large horizons. Experimental results on 100 challenging OGBench tasks demonstrate that the proposed method outperforms competitive baselines, particularly on tasks with highly suboptimal datasets and those requiring long-horizon reasoning. Project page: https://rllab-snu.github.io/projects/UHM/

Hogun Kee, Wooseok Oh, Minjae Kang et al.

In this paper, we present the tidiness score-guided Monte Carlo tree search (TSMCTS), a novel framework designed to address the tabletop tidying up problem using only an RGB-D camera. We address two major problems for tabletop tidying up problem: (1) the lack of public datasets and benchmarks, and (2) the difficulty of specifying the goal configuration of unseen objects. We address the former by presenting the tabletop tidying up (TTU) dataset, a structured dataset collected in simulation. Using this dataset, we train a vision-based discriminator capable of predicting the tidiness score. This discriminator can consistently evaluate the degree of tidiness across unseen configurations, including real-world scenes. Addressing the second problem, we employ Monte Carlo tree search (MCTS) to find tidying trajectories without specifying explicit goals. Instead of providing specific goals, we demonstrate that our MCTS-based planner can find diverse tidied configurations using the tidiness score as a guidance. Consequently, we propose TSMCTS, which integrates a tidiness discriminator with an MCTS-based tidying planner to find optimal tidied arrangements. TSMCTS has successfully demonstrated its capability across various environments, including coffee tables, dining tables, office desks, and bathrooms. The TTU dataset is available at: https://github.com/rllab-snu/TTU-Dataset.

Mineui Hong, Minjae Kang, Songhwai Oh

Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as long-term planning, vision-based control, and multi-task decision-making. To this end, we propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space and to have an agent to follow the milestones to accomplish a given task. The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control. Furthermore, our approach exploits generation flexibility of the diffusion model, which makes it possible to plan diverse trajectories for multi-task decision-making. We demonstrate the proposed method across offline reinforcement learning (RL) benchmarks and an visual manipulation environment. The results show that our approach outperforms offline RL methods in solving long-horizon, sparse-reward tasks and multi-task problems, while also achieving the state-of-the-art performance on the most challenging vision-based manipulation benchmark.

Hojun Chung, Junseo Lee, Minsoo Kim et al.

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://rllab-snu.github.io/projects/ADD

Dohyeong Kim, Mineui Hong, Jeongho Park et al.

In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propose a constrained multi-objective RL algorithm named Constrained Multi-Objective Gradient Aggregator (CoMOGA). In the field of multi-objective optimization, managing conflicts between the gradients of the multiple objectives is crucial to prevent policies from converging to local optima. It is also essential to efficiently handle safety constraints for stable training and constraint satisfaction. We address these challenges straightforwardly by treating the maximization of multiple objectives as a constrained optimization problem (COP), where the constraints are defined to improve the original objectives. Existing safety constraints are then integrated into the COP, and the policy is updated using a linear approximation, which ensures the avoidance of gradient conflicts. Despite its simplicity, CoMOGA guarantees optimal convergence in tabular settings. Through various experiments, we have confirmed that preventing gradient conflicts is critical, and the proposed method achieves constraint satisfaction across all tasks.

Gunmin Lee, Wooseok Oh, Seungyoun Shin et al.

In this paper, we consider the problem of autonomous driving using imitation learning in a semi-supervised manner. In particular, both labeled and unlabeled demonstrations are leveraged during training by estimating the quality of each unlabeled demonstration. If the provided demonstrations are corrupted and have a low signal-to-noise ratio, the performance of the imitation learning agent can be degraded significantly. To mitigate this problem, we propose a method called semi-supervised imitation learning (SSIL). SSIL first learns how to discriminate and evaluate each state-action pair's reliability in unlabeled demonstrations by assigning higher reliability values to demonstrations similar to labeled expert demonstrations. This reliability value is called leverage. After this discrimination process, both labeled and unlabeled demonstrations with estimated leverage values are utilized while training the policy in a semi-supervised manner. The experimental results demonstrate the validity of the proposed algorithm using unlabeled trajectories with mixed qualities. Moreover, the hardware experiments using an RC car are conducted to show that the proposed method can be applied to real-world applications.

Jeongwoo Oh, Gunmin Lee, Jeongeun Park et al.

Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods to the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. The dataset of this paper can be downloaded from https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html.

Hyemin Ahn, Obin Kwon, Kyoungdo Kim et al.

This paper emphasizes the importance of a robot's ability to refer to its task history, especially when it executes a series of pick-and-place manipulations by following language instructions given one by one. The advantage of referring to the manipulation history can be categorized into two folds: (1) the language instructions omitting details but using expressions referring to the past can be interpreted, and (2) the visual information of objects occluded by previous manipulations can be inferred. For this, we introduce a history-dependent manipulation task which objective is to visually ground a series of language instructions for proper pick-and-place manipulations by referring to the past. We also suggest a relevant dataset and model which can be a baseline, and show that our model trained with the proposed dataset can also be applied to the real world based on the CycleGAN. Our dataset and code are publicly available on the project website: https://sites.google.com/view/history-dependent-manipulation.

Kyungjae Lee, Hongjun Yang, Sungbin Lim et al.

In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose $p$-th moment is bounded by a constant $ν_{p}$ for $1<p\leq2$. First, we propose a novel robust estimator which does not require $ν_{p}$ as prior information, while other existing robust estimators demand prior knowledge about $ν_{p}$. We show that an error probability of the proposed estimator decays exponentially fast. Using this estimator, we propose a perturbation-based exploration strategy and develop a generalized regret analysis scheme that provides upper and lower regret bounds by revealing the relationship between the regret and the cumulative density function of the perturbation. From the proposed analysis scheme, we obtain gap-dependent and gap-independent upper and lower regret bounds of various perturbations. We also find the optimal hyperparameters for each perturbation, which can achieve the minimax optimal regret bound with respect to total rounds. In simulation, the proposed estimator shows favorable performance compared to existing robust estimators for various $p$ values and, for MAB problems, the proposed perturbation strategy outperforms existing exploration methods.

Hyemin Ahn, Jaehun Kim, Kihyun Kim et al.

This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic 3D human dancing move from music, which can be applied to artificial agents and humanoid robots. The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5,000 pose frames. Experimental results of generated dance sequences from various songs show how the proposed method generates human-like dancing move to a given music. In addition, a generated 3D dance sequence is applied to a humanoid robot, showing that the proposed framework can make a robot to dance just by listening to music.

Chanho Ahn, Eunwoo Kim, Songhwai Oh

In this work, we consider the problem of instance-wise dynamic network model selection for multi-task learning. To this end, we propose an efficient approach to exploit a compact but accurate model in a backbone architecture for each instance of all tasks. The proposed method consists of an estimator and a selector. The estimator is based on a backbone architecture and structured hierarchically. It can produce multiple different network models of different configurations in a hierarchical structure. The selector chooses a model dynamically from a pool of candidate models given an input instance. The selector is a relatively small-size network consisting of a few layers, which estimates a probability distribution over the candidate models when an input instance of a task is given. Both estimator and selector are jointly trained in a unified learning framework in conjunction with a sampling-based learning strategy, without additional computation steps. We demonstrate the proposed approach for several image classification tasks compared to existing approaches performing model selection or learning multiple tasks. Experimental results show that our approach gives not only outstanding performance compared to other competitors but also the versatility to perform instance-wise model selection for multiple tasks.

Eunwoo Kim, Chanho Ahn, Philip H. S. Torr et al.

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning for multiple tasks. To this end, we propose a novel network architecture producing multiple networks of different configurations, termed deep virtual networks (DVNs), for different tasks. Each DVN is specialized for a single task and structured hierarchically. The hierarchical structure, which contains multiple levels of hierarchy corresponding to different numbers of parameters, enables multiple inference for different memory budgets. The building block of a deep virtual network is based on a disjoint collection of parameters of a network, which we call a unit. The lowest level of hierarchy in a deep virtual network is a unit, and higher levels of hierarchy contain lower levels' units and other additional units. Given a budget on the number of parameters, a different level of a deep virtual network can be chosen to perform the task. A unit can be shared by different DVNs, allowing multiple DVNs in a single network. In addition, shared units provide assistance to the target task with additional knowledge learned from another tasks. This cooperative configuration of DVNs makes it possible to handle different tasks in a memory-aware manner. Our experiments show that the proposed method outperforms existing approaches for multiple tasks. Notably, ours is more efficient than others as it allows memory-aware inference for all tasks.

Hyemin Ahn, Sungjoon Choi, Nuri Kim et al.

In this paper, we propose the Interactive Text2Pickup (IT2P) network for human-robot collaboration which enables an effective interaction with a human user despite the ambiguity in user's commands. We focus on the task where a robot is expected to pick up an object instructed by a human, and to interact with the human when the given instruction is vague. The proposed network understands the command from the human user and estimates the position of the desired object first. To handle the inherent ambiguity in human language commands, a suitable question which can resolve the ambiguity is generated. The user's answer to the question is combined with the initial command and given back to the network, resulting in more accurate estimation. The experiment results show that given unambiguous commands, the proposed method can estimate the position of the requested object with an accuracy of 98.49% based on our test dataset. Given ambiguous language commands, we show that the accuracy of the pick up task increases by 1.94 times after incorporating the information obtained from the interaction.

Nuri Kim, Donghoon Lee, Songhwai Oh

Recent object detectors find instances while categorizing candidate regions. As each region is evaluated independently, the number of candidate regions from a detector is usually larger than the number of objects. Since the final goal of detection is to assign a single detection to each object, a heuristic algorithm, such as non-maximum suppression (NMS), is used to select a single bounding box for an object. While simple heuristic algorithms are effective for stand-alone objects, they can fail to detect overlapped objects. In this paper, we address this issue by training a network to distinguish different objects using the relationship between candidate boxes. We propose an instance-aware detection network (IDNet), which can learn to extract features from candidate regions and measure their similarities. Based on pairwise similarities and detection qualities, the IDNet selects a subset of candidate bounding boxes using instance-aware determinantal point process inference (IDPP). Extensive experiments demonstrate that the proposed algorithm achieves significant improvements for detecting overlapped objects compared to existing state-of-the-art detection methods on the PASCAL VOC and MS COCO datasets.

Kyungjae Lee, Sungjoon Choi, Songhwai Oh

In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown to be a sparsemax distribution, whose supporting set can be adjusted. The proposed method has advantages over a softmax distribution in that it can exclude unnecessary actions by assigning zero probability. Second, we prove that an MCTE problem is equivalent to robust Bayes estimation in the sense of the Brier score. Third, we propose a maximum causal Tsallis entropy imitation learning (MCTEIL) algorithm with a sparse mixture density network (sparse MDN) by modeling mixture weights using a sparsemax distribution. In particular, we show that the causal Tsallis entropy of an MDN encourages exploration and efficient mixture utilization while Boltzmann Gibbs entropy is less effective. We validate the proposed method in two simulation studies and MCTEIL outperforms existing imitation learning methods in terms of average returns and learning multi-modal policies.

Geonho Cha, Minsik Lee, Jungchan Cho et al.

In this paper, we address the problem of estimating a 3D human pose from a single image, which is important but difficult to solve due to many reasons, such as self-occlusions, wild appearance changes, and inherent ambiguities of 3D estimation from a 2D cue. These difficulties make the problem ill-posed, which have become requiring increasingly complex estimators to enhance the performance. On the other hand, most existing methods try to handle this problem based on a single complex estimator, which might not be good solutions. In this paper, to resolve this issue, we propose a multiple-partial-hypothesis-based framework for the problem of estimating 3D human pose from a single image, which can be fine-tuned in an end-to-end fashion. We first select several joint groups from a human joint model using the proposed sampling scheme, and estimate the 3D poses of each joint group separately based on deep neural networks. After that, they are aggregated to obtain the final 3D poses using the proposed robust optimization formula. The overall procedure can be fine-tuned in an end-to-end fashion, resulting in better performance. In the experiments, the proposed framework shows the state-of-the-art performances on popular benchmark data sets, namely Human3.6M and HumanEva, which demonstrate the effectiveness of the proposed framework.

Donghoon Lee, Ming-Hsuan Yang, Songhwai Oh

Single image reflection separation is an ill-posed problem since two scenes, a transmitted scene and a reflected scene, need to be inferred from a single observation. To make the problem tractable, in this work we assume that categories of two scenes are known. It allows us to address the problem by generating both scenes that belong to the categories while their contents are constrained to match with the observed image. A novel network architecture is proposed to render realistic images of both scenes based on adversarial learning. The network can be trained in a weakly supervised manner, i.e., it learns to separate an observed image without corresponding ground truth images of transmission and reflection scenes which are difficult to collect in practice. Experimental results on real and synthetic datasets demonstrate that the proposed algorithm performs favorably against existing methods.

Eunwoo Kim, Chanho Ahn, Songhwai Oh

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded weight parameters, it is not possible to apply a single deep architecture for multiple devices with different resources. When a new device or circumstantial condition requires a new deep architecture, it is necessary to construct and train a new network from scratch. In this work, we propose a novel deep learning framework, called a nested sparse network, which exploits an n-in-1-type nested structure in a neural network. A nested sparse network consists of multiple levels of networks with a different sparsity ratio associated with each level, and higher level networks share parameters with lower level networks to enable stable nested learning. The proposed framework realizes a resource-aware versatile architecture as the same network can meet diverse resource requirements. Moreover, the proposed nested network can learn different forms of knowledge in its internal networks at different levels, enabling multiple tasks using a single network, such as coarse-to-fine hierarchical classification. In order to train the proposed nested sparse network, we propose efficient weight connection learning and channel and layer scheduling strategies. We evaluate our network in multiple tasks, including adaptive deep compression, knowledge distillation, and learning class hierarchy, and demonstrate that nested sparse networks perform competitively, but more efficiently, compared to existing methods.

Hyemin Ahn, Timothy Ha, Yunho Choi et al.

In this paper, we propose a generative model which learns the relationship between language and human action in order to generate a human action sequence given a sentence describing human behavior. The proposed generative model is a generative adversarial network (GAN), which is based on the sequence to sequence (SEQ2SEQ) model. Using the proposed generative network, we can synthesize various actions for a robot or a virtual agent using a text encoder recurrent neural network (RNN) and an action decoder RNN. The proposed generative network is trained from 29,770 pairs of actions and sentence annotations extracted from MSR-Video-to-Text (MSR-VTT), a large-scale video dataset. We demonstrate that the network can generate human-like actions which can be transferred to a Baxter robot, such that the robot performs an action based on a provided sentence. Results show that the proposed generative network correctly models the relationship between language and action and can generate a diverse set of actions from the same sentence.

Kyungjae Lee, Sungjoon Choi, Songhwai Oh

In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyze the optimality condition of a sparse MDP. Then, we propose a sparse value iteration method which solves a sparse MDP and then prove the convergence and optimality of sparse value iteration using the Banach fixed point theorem. The proposed sparse MDP is compared to soft MDPs which utilize causal entropy regularization. We show that the performance error of a sparse MDP has a constant bound, while the error of a soft MDP increases logarithmically with respect to the number of actions, where this performance error is caused by the introduced regularization term. In experiments, we apply sparse MDPs to reinforcement learning problems. The proposed method outperforms existing methods in terms of the convergence speed and performance.

Sungjoon Choi, Kyungjae Lee, H. Andy Park et al.

In this paper, we present a novel nonparametric motion flow model that effectively describes a motion trajectory of a human and its application to human robot cooperation. To this end, motion flow similarity measure which considers both spatial and temporal properties of a trajectory is proposed by utilizing the mean and variance functions of a Gaussian process. We also present a human robot cooperation method using the proposed motion flow model. Given a set of interacting trajectories of two workers, the underlying reward function of cooperating behaviors is optimized by using the learned motion description as an input to the reward function where a stochastic trajectory optimization method is used to control a robot. The presented human robot cooperation method is compared with the state-of-the-art algorithm, which utilizes a mixture of interaction primitives (MIP), in terms of the RMS error between generated and target trajectories. While the proposed method shows comparable performance with the MIP when the full observation of human demonstrations is given, it shows superior performance with respect to given partial trajectory information.

Sungjoon Choi, Kyungjae Lee, Sungbin Lim et al.

In this paper, we propose an uncertainty-aware learning from demonstration method by presenting a novel uncertainty estimation method utilizing a mixture density network appropriate for modeling complex and noisy human behaviors. The proposed uncertainty acquisition can be done with a single forward path without Monte Carlo sampling and is suitable for real-time robotics applications. The properties of the proposed uncertainty measure are analyzed through three different synthetic examples, absence of data, heavy measurement noise, and composition of functions scenarios. We show that each case can be distinguished using the proposed uncertainty measure and presented an uncertainty-aware learn- ing from demonstration method of an autonomous driving using this property. The proposed uncertainty-aware learning from demonstration method outperforms other compared methods in terms of safety using a complex real-world driving dataset.

Donghoon Lee, Sangdoo Yun, Sungjoon Choi et al.

We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior. In this work, key local patches are defined as informative regions of the target object or scene. This is a challenging problem since it requires generating realistic images and predicting locations of parts at the same time. We construct adversarial networks to tackle this problem. A generator network generates a fake image as well as a mask based on the encoder-decoder framework. On the other hand, a discriminator network aims to detect fake images. The network is trained with three losses to consider spatial, appearance, and adversarial information. The spatial loss determines whether the locations of predicted parts are correct. Input patches are restored in the output image without much modification due to the appearance loss. The adversarial loss ensures output images are realistic. The proposed network is trained without supervisory signals since no labels of key parts are required. Experimental results on six datasets demonstrate that the proposed algorithm performs favorably on challenging objects and scenes.

Sungjoon Choi, Kyungjae Lee, Andy Park et al.

In this paper, we focus on the problem of inferring the underlying reward function of an expert given demonstrations, which is often referred to as inverse reinforcement learning (IRL). In particular, we propose a model-free density-based IRL algorithm, named density matching reward learning (DMRL), which does not require model dynamics. The performance of DMRL is analyzed theoretically and the sample complexity is derived. Furthermore, the proposed DMRL is extended to handle nonlinear IRL problems by assuming that the reward function is in the reproducing kernel Hilbert space (RKHS) and kernel DMRL (KDMRL) is proposed. The parameters for KDMRL can be computed analytically, which greatly reduces the computation time. The performance of KDMRL is extensively evaluated in two sets of experiments: grid world and track driving experiments. In grid world experiments, the proposed KDMRL method is compared with both model-based and model-free IRL methods and shows superior performance on a nonlinear reward setting and competitive performance on a linear reward setting in terms of expected value differences. Then we move on to more realistic experiments of learning different driving styles for autonomous navigation in complex and dynamic tracks using KDMRL and receding horizon control.