Related papers: Enabling Adaptive Agent Training in Open-Ended Sim…
Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts…
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in…
Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in…
Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simulation, and then…
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that…
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…
Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share characteristics with the ones they have encountered during training.…
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL). In this work, we demonstrate that…
While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated…
Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been…
Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently…
Unsupervised Domain Adaptation (UDA) aims at improving the generalization capability of a model trained on a source domain to perform well on a target domain for which no labeled data is available. In this paper, we consider the semantic…
Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer…
Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate high-dimensional information across visual, temporal,…
Computers can understand and then engage with people in an emotionally intelligent way thanks to speech-emotion recognition (SER). However, the performance of SER in cross-corpus and real-world live data feed scenarios can be significantly…
Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each…
Domain Randomization (DR) is commonly used for sim2real transfer of reinforcement learning (RL) policies in robotics. Most DR approaches require a simulator with a fixed set of tunable parameters from the start of the training, from which…
Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…
A key limitation preventing the wider adoption of autonomous agents trained via deep reinforcement learning (RL) is their limited ability to generalise to new environments, even when these share similar characteristics with environments…