Related papers: Backward Learning for Goal-Conditioned Policies
Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…
To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target squares. We find this network pursues multiple…
Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to…
Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each change of the target policy, its value is estimated from the…
Reward machines are automaton-like structures that capture the memory required to accomplish a multi-stage task. When combined with reinforcement learning or optimal control methods, they can be used to synthesize robot policies to achieve…
Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…
Getting up from an arbitrary fallen state is a basic human skill. Existing methods for learning this skill often generate highly dynamic and erratic get-up motions, which do not resemble human get-up strategies, or are based on tracking…
Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment. While in real-world scenarios,…
Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired to the target task.…
We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challenges of learning…
State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…
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…
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…
Machine learning algorithms learn to solve a task, but are unable to improve their ability to learn. Meta-learning methods learn about machine learning algorithms and improve them so that they learn more quickly. However, existing…
Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations. The commonplace scarcity and heterogeneous sources of such demonstrations can lead to the…
A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postulate that in the absence of useful reward signals, an effective exploration strategy should seek out…
Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…
Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…