Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing
complex robotic behaviors. But training DRL models is incredibly compute and memory …

Deep reinforcement learning (DRL) has shown remarkable success in simulation domains,
yet its application in designing robot controllers remains limited, due to its single-task …

The emergence of differentiable simulators enabling analytic gradient computation has
motivated a new wave of learning algorithms that hold the potential to significantly increase …

Deep reinforcement learning (RL) uses model-free techniques to optimize task-specific
control policies. Despite having emerged as a promising approach for complex problems …

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex
robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient …

Deep reinforcement learning (RL) can enable robots to autonomously acquire complex
behaviors, such as legged locomotion. However, RL in the real world is complicated by …

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static
behavior datasets into policies that can perform better than the policy that collected the data …

Deep Reinforcement Learning (DRL) has made tremendous advances in both simulated
and real-world robot control tasks in recent years. Nevertheless, applying DRL to novel robot …

Deep reinforcement learning is a promising approach to learning policies in unstructured
environments. Due to its sample inefficiency, though, deep RL applications have primarily …

Recent breakthroughs in the reinforcement learning (RL) community have made significant
advances towards learning and deploying policies on real world robotic systems. However …