From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning

Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, naturally navigate this balance by transitioning from free exploration with sparse rewards to goal-directed behavior guided by increasingly dense rewards. Inspired by this natural progression, we investigate the Toddler-Inspired Reward Transition in goal-oriented RL tasks. Our study focuses on transitioning from sparse to potential-based dense (S2D) rewards while preserving optimal strategies. Through experiments on dynamic robotic arm manipulation and egocentric 3D navigation tasks, we demonstrate that effective S2D reward transitions significantly enhance learning performance and sample efficiency. Additionally, using a Cross-Density Visualizer, we show that S2D transitions smooth the policy loss landscape, resulting in wider minima that improve generalization in RL models. In addition, we reinterpret Tolman's maze experiments, underscoring the critical role of early free exploratory learning in the context of S2D rewards.

On the Consistency of Video Large Language Models in Temporal Comprehension

Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations in video contents, language queries, and task settings, unveiling severe deficiencies in maintaining consistency. We further explore common prompting and instruction-tuning methods as potential solutions, but find that their improvements are often unstable. To that end, we propose event temporal verification tuning that explicitly accounts for consistency, and demonstrate significant improvements for both grounding and consistency. Our data and code will be available at https://github.com/minjoong507/Consistency-of-Video-LLM.

CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision

This paper explores how non-experts can teach robots desired skills in their environments. We argue that natural language is an intuitive and accessible interface for robot learning. To this end, we investigate two key aspects: (1) how non-experts collect robotic data using natural language supervision and (2) how pre-trained vision-language models learn end-to-end policies directly from this supervision. We propose a data collection framework that collects robot demonstrations based on natural language supervision (e.g., "move forward") and further augments these demonstrations. Next, we introduce a model that learns language-conditioned policies from natural language supervision called CLIP-RT. Our model employs pre-trained CLIP models and learns to predict actions represented in language via contrastive imitation learning. We first train CLIP-RT on large-scale robotic data and then enable it to learn desired skills using data collected from our framework. CLIP-RT shows strong capabilities in acquiring novel manipulation skills, outperforming the state-of-the-art model, OpenVLA (7B parameters), by 17% in average success rates, while using 7x fewer parameters (1B).

HAPFI: History-Aware Planning based on Fused Information

Embodied Instruction Following (EIF) is a task of planning a long sequence of sub-goals given high-level natural language instructions, such as "Rinse a slice of lettuce and place on the white table next to the fork". To successfully execute these long-term horizon tasks, we argue that an agent must consider its past, i.e., historical data, when making decisions in each step. Nevertheless, recent approaches in EIF often neglects the knowledge from historical data and also do not effectively utilize information across the modalities. To this end, we propose History-Aware Planning based on Fused Information (HAPFI), effectively leveraging the historical data from diverse modalities that agents collect while interacting with the environment. Specifically, HAPFI integrates multiple modalities, including historical RGB observations, bounding boxes, sub-goals, and high-level instructions, by effectively fusing modalities via our Mutually Attentive Fusion method. Through experiments with diverse comparisons, we show that an agent utilizing historical multi-modal information surpasses all the compared methods that neglect the historical data in terms of action planning capability, enabling the generation of well-informed action plans for the next step. Moreover, we provided qualitative evidence highlighting the significance of leveraging historical multi-modal data, particularly in scenarios where the agent encounters intermediate failures, showcasing its robust re-planning capabilities.

Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning

Causal dynamics learning has recently emerged as a promising approach to enhancing robustness in reinforcement learning (RL). Typically, the goal is to build a dynamics model that makes predictions based on the causal relationships among the entities. Despite the fact that causal connections often manifest only under certain contexts, existing approaches overlook such fine-grained relationships and lack a detailed understanding of the dynamics. In this work, we propose a novel dynamics model that infers fine-grained causal structures and employs them for prediction, leading to improved robustness in RL. The key idea is to jointly learn the dynamics model with a discrete latent variable that quantizes the state-action space into subgroups. This leads to recognizing meaningful context that displays sparse dependencies, where causal structures are learned for each subgroup throughout the training. Experimental results demonstrate the robustness of our method to unseen states and locally spurious correlations in downstream tasks where fine-grained causal reasoning is crucial. We further illustrate the effectiveness of our subgroup-based approach with quantization in discovering fine-grained causal relationships compared to prior methods.

Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction

Monte Carlo Tree Search (MCTS) has showcased its efficacy across a broad spectrum of decision-making problems. However, its performance often degrades under vast combinatorial action space, especially where an action is composed of multiple sub-actions. In this work, we propose an action abstraction based on the compositional structure between a state and sub-actions for improving the efficiency of MCTS under a factored action space. Our method learns a latent dynamics model with an auxiliary network that captures sub-actions relevant to the transition on the current state, which we call state-conditioned action abstraction. Notably, it infers such compositional relationships from high-dimensional observations without the known environment model. During the tree traversal, our method constructs the state-conditioned action abstraction for each node on-the-fly, reducing the search space by discarding the exploration of redundant sub-actions. Experimental results demonstrate the superior sample efficiency of our method compared to vanilla MuZero, which suffers from expansive action space.

On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition

Conditional independence provides a way to understand causal relationships among the variables of interest. An underlying system may exhibit more fine-grained causal relationships especially between a variable and its parents, which will be called the local independence relationships. One of the most widely studied local relationships is Context-Specific Independence (CSI), which holds in a specific assignment of conditioned variables. However, its applicability is often limited since it does not allow continuous variables: data conditioned to the specific value of a continuous variable contains few instances, if not none, making it infeasible to test independence. In this work, we define and characterize the local independence relationship that holds in a specific set of joint assignments of parental variables, which we call context-set specific independence (CSSI). We then provide a canonical representation of CSSI and prove its fundamental properties. Based on our theoretical findings, we cast the problem of discovering multiple CSSI relationships in a system as finding a partition of the joint outcome space. Finally, we propose a novel method, coined neural contextual decomposition (NCD), which learns such partition by imposing each set to induce CSSI via modeling a conditional distribution. We empirically demonstrate that the proposed method successfully discovers the ground truth local independence relationships in both synthetic dataset and complex system reflecting the real-world physical dynamics.

ActiveNeuS: Active 3D Reconstruction using Neural Implicit Surface Uncertainty

Active learning in 3D scene reconstruction has been widely studied, as selecting informative training views is critical for the reconstruction. Recently, Neural Radiance Fields (NeRF) variants have shown performance increases in active 3D reconstruction using image rendering or geometric uncertainty. However, the simultaneous consideration of both uncertainties in selecting informative views remains unexplored, while utilizing different types of uncertainty can reduce the bias that arises in the early training stage with sparse inputs. In this paper, we propose ActiveNeuS, which evaluates candidate views considering both uncertainties. ActiveNeuS provides a way to accumulate image rendering uncertainty while avoiding the bias that the estimated densities can introduce. ActiveNeuS computes the neural implicit surface uncertainty, providing the color uncertainty along with the surface information. It efficiently handles the bias by using the surface information and a grid, enabling the fast selection of diverse viewpoints. Our method outperforms previous works on popular datasets, Blender and DTU, showing that the views selected by ActiveNeuS significantly improve performance.

Unsupervised Dynamics Prediction with Object-Centric Kinematics

Human perception involves discerning complex multi-object scenes into time-static object appearance (\ie, size, shape, color) and time-varying object motion (\ie, location, velocity, acceleration). This innate ability to unconsciously understand the environment is the motivation behind the success of dynamics modeling. Object-centric representations have emerged as a promising tool for dynamics prediction, yet they primarily focus on the objects' appearance, often overlooking other crucial attributes. In this paper, we propose Object-Centric Kinematics (OCK), a framework for dynamics prediction leveraging object-centric representations. Our model utilizes a novel component named object kinematics, which comprises low-level structured states of objects' position, velocity, and acceleration. The object kinematics are obtained via either implicit or explicit approaches, enabling comprehensive spatiotemporal object reasoning, and integrated through various transformer mechanisms, facilitating effective object-centric dynamics modeling. Our model demonstrates superior performance when handling objects and backgrounds in complex scenes characterized by a wide range of object attributes and dynamic movements. Moreover, our model demonstrates generalization capabilities across diverse synthetic environments, highlighting its potential for broad applicability in vision-related tasks.

Socratic Planner: Inquiry-Based Zero-Shot Planning for Embodied Instruction Following

Embodied Instruction Following (EIF) is the task of executing natural language instructions by navigating and interacting with objects in 3D environments. One of the primary challenges in EIF is compositional task planning, which is often addressed with supervised or in-context learning with labeled data. To this end, we introduce the Socratic Planner, the first zero-shot planning method that infers without the need for any training data. Socratic Planner first decomposes the instructions into substructural information of the task through self-questioning and answering, translating it into a high-level plan, i.e., a sequence of subgoals. Subgoals are executed sequentially, with our visually grounded re-planning mechanism adjusting plans dynamically through a dense visual feedback. We also introduce an evaluation metric of high-level plans, RelaxedHLP, for a more comprehensive evaluation. Experiments demonstrate the effectiveness of the Socratic Planner, achieving competitive performance on both zero-shot and few-shot task planning in the ALFRED benchmark, particularly excelling in tasks requiring higher-dimensional inference. Additionally, a precise adjustments in the plan were achieved by incorporating environmental visual information.