Related papers: BlockPuzzle - A Challenge in Physical Reasoning an…

Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low…

Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs still struggle with spatial transformations and multi-step…

Reinforcement learning (RL) problems can be challenging without well-shaped rewards. Prior work on provably efficient RL methods generally proposes to address this issue with dedicated exploration strategies. However, another way to tackle…

It is well known that it is difficult to have a reliable and robust framework to link multi-agent deep reinforcement learning algorithms with practical multi-robot applications. To fill this gap, we propose and build an open-source…

Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on…

Reinforcement learning algorithms can train agents that solve problems in complex, interesting environments. Normally, the complexity of the trained agent is closely related to the complexity of the environment. This suggests that a highly…

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

One of the grand challenges of reinforcement learning is the ability to generalize to new tasks. However, general agents require a set of rich, diverse tasks to train on. Designing a `foundation environment' for such tasks is tricky -- the…

Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task. In this paper we address this problem by introducing a notion of imaginary object goals. For a given manipulation…

Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized…

In this paper, a comparison of reinforcement learning algorithms and their performance on a robot box pushing task is provided. The robot box pushing problem is structured as both a single-agent problem and also a multi-agent problem. A…

Physical construction---the ability to compose objects, subject to physical dynamics, to serve some function---is fundamental to human intelligence. We introduce a suite of challenging physical construction tasks inspired by how children…

The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and…

While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural…

Classical robotic systems typically rely on custom planners designed for constrained environments. While effective in restricted settings, these systems lack generalization capabilities, limiting the scalability of embodied AI and…

We consider task allocation for multi-object transport using a multi-robot system, in which each robot selects one object among multiple objects with different and unknown weights. The existing centralized methods assume the number of…

One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function. Any misalignment between the reward and the desired behavior can result…

The combined approach of the Qualitative Reasoning and Probabilistic Functions for the knowledge representation is proposed. The method aims at represent uncertain, qualitative knowledge that is essential for the moving blocks task's…

The OpenAI Gym provides researchers and enthusiasts with simple to use environments for reinforcement learning. Even the simplest environment have a level of complexity that can obfuscate the inner workings of RL approaches and make…

Robotic simulators are crucial for academic research and education as well as the development of safety-critical applications. Reinforcement learning environments -- simple simulations coupled with a problem specification in the form of a…