相关论文: Bridging the Imitation Gap by Adaptive Insubordina…

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In…

Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical,…

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which…

In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods…

To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model…

Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents must efficiently explore vast worlds, assign credit from delayed…

The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…

Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment…

In robotics, a common challenge in imitation learning is the mismatch between training and deployment conditions, caused, for example, by environmental changes or imperfect observation and control. When a robot follows a nominal trajectory…

Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…

Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to observe behavior in the real-world, the underlying actions may…

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Human teaching effort is a significant bottleneck for the broader applicability of interactive imitation learning. To reduce the number of required queries, existing methods employ active learning to query the human teacher only in…

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call…

As the number of the robot's degrees of freedom increases, the implementation of robot motion becomes more complex and difficult. In this study, we focus on learning 6DOF-grasping motion and consider dividing the grasping motion into…

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Modern multi-agent systems ranging from sensor networks monitoring critical infrastructure to crowdsourcing platforms aggregating human intelligence can suffer significant performance degradation due to systematic biases that vary with…

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algorithmic machine teaching focuses on the batch setting, where…