相关论文: Statistical Guarantees for Offline Domain Randomiz…

In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization…

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is…

We consider the problem of offline reinforcement learning with model-based control, whose goal is to learn a dynamics model from the experience replay and obtain a pessimism-oriented agent under the learned model. Current model-based…

Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment…

Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we…

Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality…

The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL is the distribution…

Offline reinforcement learning aims to learn from pre-collected datasets without active exploration. This problem faces significant challenges, including limited data availability and distributional shifts. Existing approaches adopt a…

Learning visuomotor policies in simulation is much safer and cheaper than in the real world. However, due to discrepancies between the simulated and real data, simulator-trained policies often fail when transferred to real robots. One…

Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising…

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…

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Domain Randomization (DR) is known to require a significant amount of training data for good performance. We argue that this is due to DR's strategy of random data generation using a uniform distribution over simulation parameters, as a…

Domain randomization (DR) enables sim-to-real transfer by training controllers on a distribution of simulated environments, with the goal of achieving robust performance in the real world. Although DR is widely used in practice and is often…

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly…

Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hinges on the choice of the sampling distribution of the…

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…

We consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of…

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…