Nir Lipovetzky

Classical Planning Algorithms on the Atari Video Games

2015

The Atari 2600 games supported in the Arcade Learning Environment [Bellemare et al., 2013] all feature a known initial (RAM) state and actions that have deterministic effects. Classical planners, however, cannot be used off-the-shelf as …

Handling non-local dead-ends in Agent Planning Programs

2017

We propose an approach to reason about agent planning programs with global information. Agent planning programs can be understood as a network of planning tasks, accommodating long-term goals, non-terminating behaviors, and interactive execution. We provide …

Behaviour Recognition with Kinodynamic Planning Over Continuous Domains

2021 · Frontiers in Artificial Intelligence

recognition over complex continuous domains using model predictive control (MPC) for trajectory generation. We formally define the problem of kinodynamic behaviour recognition and establish a set of baseline behaviours and performance measures in the complex …

A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents

2023 · arXiv (Cornell University)

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves training a …