Related papers: Distilled Domain Randomization
Autonomous navigation in unstructured environments is essential for field and planetary robotics, where robots must efficiently reach goals while avoiding obstacles under uncertain conditions. Conventional algorithmic approaches often…
The sample inefficiency of reinforcement learning (RL) remains a significant challenge in robotics. RL requires large-scale simulation and can still cause long training times, slowing research and innovation. This issue is particularly…
Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…
Deep Reinforcement Learning (DRL) is emerging as a promising approach to generate adaptive behaviors for robotic platforms. However, a major drawback of using DRL is the data-hungry training regime that requires millions of trial and error…
While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry…
Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it…
Diffusion models have demonstrated excellent potential for generating diverse images. However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as a remedy…
In the ever-changing and intricate landscape of financial markets, portfolio optimisation remains a formidable challenge for investors and asset managers. Conventional methods often struggle to capture the complex dynamics of market…
In this paper, we argue that mutual distillation between reinforcement learning policies serves as an implicit regularization, preventing them from overfitting to irrelevant features. We highlight two separate contributions: (i)…
Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…
Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly…
Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space: typically, a goal can be accomplished in multiple ways,…
Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…
Robotic systems driven by artificial muscles present unique challenges due to the nonlinear dynamics of actuators and the complex designs of mechanical structures. Traditional model-based controllers often struggle to achieve desired…
Learning a good state representation is a critical skill when dealing with multiple tasks in Reinforcement Learning as it allows for transfer and better generalization between tasks. However, defining what constitute a useful representation…
We study how to exploit dense simulator-defined rewards in vision-based autonomous driving without inheriting their misalignment with deployment metrics. In realistic simulators such as CARLA, privileged state (e.g., lane geometry,…
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…
Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…
Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent. Since the RM contains all state observations and action policy history, it may incur huge communication…
Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…