Related papers: Planning with Goal-Conditioned Policies
When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…
While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Real-world decision-making tasks typically occur in complex and open environments, posing significant challenges to reinforcement learning (RL) agents' exploration efficiency and long-horizon planning capabilities. A promising approach is…
Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…
Solving robotic navigation tasks via reinforcement learning (RL) is challenging due to their sparse reward and long decision horizon nature. However, in many navigation tasks, high-level (HL) task representations, like a rough floor plan,…
Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…
State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy networks, or a combination of policy networks and planning. Hybrid approaches that combine…
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…
Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the…
Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…
Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent…
This paper proposes a safe reinforcement learning (RL) framework based on forward-invariance-induced action-space design. The control problem is cast as a Markov decision process, but instead of relying on runtime shielding or penalty-based…
Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains. However, they are typically handcrafted and tend to require precise formulations that are not…
In model-based reinforcement learning (MBRL), Wan et al. (2019) showed conditions under which the environment model could produce the expectation of the next feature vector rather than the full distribution, or a sample thereof, with no…
Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…
In this paper, we propose a model-free reinforcement learning method to synthesize control policies for motion planning problems with continuous states and actions. The robot is modelled as a labeled discrete-time Markov decision process…
Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL,…
We prove a fundamental limitation on the efficiency of a wide class of Reinforcement Learning (RL) algorithms. This limitation applies to model-free RL methods as well as a broad range of model-based methods, such as planning with tree…
Although Reinforcement Learning (RL) algorithms have found tremendous success in simulated domains, they often cannot directly be applied to physical systems, especially in cases where there are hard constraints to satisfy (e.g. on safety…