Related papers: MO-Playground: Massively Parallelized Multi-Object…

Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…

Multi-objective task scheduling (MOTS) is the task scheduling while optimizing multiple and possibly contradicting constraints. A challenging extension of this problem occurs when every individual task is a multi-objective optimization…

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly…

Over the last few decades, many architectures have been developed that harness the power of neural networks to detect objects in near real-time. Training such systems requires substantial time across multiple GPUs and massive labeled…

Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward…

Meta learning with multiple objectives can be formulated as a Multi-Objective Bi-Level optimization Problem (MOBLP) where the upper-level subproblem is to solve several possible conflicting targets for the meta learner. However, existing…

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and parallelization over accelerators, Pgx can efficiently scale to…

Machine learning (ML) methods offer a wide range of configurable hyperparameters that have a significant influence on their performance. While accuracy is a commonly used performance objective, in many settings, it is not sufficient.…

Current embodied reasoning agents struggle to plan for long-horizon tasks that require to physically interact with the world to obtain the necessary information (e.g. 'sort the objects from lightest to heaviest'). The improvement of the…

Multi-robot navigation and path planning in continuous state and action spaces with uncertain environments remains an open challenge. Deep Reinforcement Learning (RL) is one of the most popular paradigms for solving this task, but its…

Quadrupedal robots are increasingly deployed for load-carrying tasks across diverse terrains. While Model Predictive Control (MPC)-based methods can account for payload variations, they often depend on predefined gait schedules or…

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new…

In reinforcement learning (RL) research, simulations enable benchmarks between algorithms, as well as prototyping and hyper-parameter tuning of agents. In order to promote RL both in research and real-world applications, frameworks are…

Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards. In this paper…

Teams of people coordinate to perform complex tasks by forming abstract mental models of world and agent dynamics. The use of abstract models contrasts with much recent work in robot learning that uses a high-fidelity simulator and…

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…

Humanoid robots have demonstrated robust locomotion capabilities using Reinforcement Learning (RL)-based approaches. Further, to obtain human-like behaviors, existing methods integrate human motion-tracking or motion prior in the RL…

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Reinforcement Learning (RL) and Imitation Learning (IL) are the standard frameworks for policy acquisition in manipulation. While IL offers efficient policy derivation, it suffers from compounding errors and distribution shift. Conversely,…