Related papers: On Discovering Algorithms for Adversarial Imitatio…
Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement…
Conditional imitation learning (CIL) trains deep neural networks, in an end-to-end manner, to mimic human driving. This approach has demonstrated suitable vehicle control when following roads, avoiding obstacles, or taking specific turns at…
Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need…
As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…
For adversarial imitation learning algorithms (AILs), no true rewards are obtained from the environment for learning the strategy. However, the pseudo rewards based on the output of the discriminator are still required. Given the implicit…
Adversarial inverse reinforcement learning (IRL) for multi-agent task allocation (MATA) is challenged by non-stationary interactions and high-dimensional coordination. Unconstrained reward inference in these settings often leads to high…
This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing…
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…
Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarantees monotonic performance improvement but requires fully…
Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally…
Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that…
Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment…
We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…
Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observation spaces prevalent in robotics. This paper addresses the…
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement…
The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a…
The performance of multi-agent reinforcement learning (MARL) in partially observable environments depends on effectively aggregating information from observations, communications, and reward signals. While most existing multi-agent systems…
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…
Though impressive results have been achieved in visual captioning, the task of generating abstract stories from photo streams is still a little-tapped problem. Different from captions, stories have more expressive language styles and…
Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective in a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in…