lilGym: Natural Language Visual Reasoning with Reinforcement Learning
This provides a new benchmark for researchers in reinforcement learning and natural language processing, though it is incremental as it builds on existing benchmark concepts.
The authors introduced lilGym, a benchmark for language-conditioned reinforcement learning in visual environments using 2,661 compositional natural language statements, and found that existing methods achieve non-trivial performance but it remains a challenging open problem.
We present lilGym, a new benchmark for language-conditioned reinforcement learning in visual environments. lilGym is based on 2,661 highly-compositional human-written natural language statements grounded in an interactive visual environment. We introduce a new approach for exact reward computation in every possible world state by annotating all statements with executable Python programs. Each statement is paired with multiple start states and reward functions to form thousands of distinct Markov Decision Processes of varying difficulty. We experiment with lilGym with different models and learning regimes. Our results and analysis show that while existing methods are able to achieve non-trivial performance, lilGym forms a challenging open problem. lilGym is available at https://lil.nlp.cornell.edu/lilgym/.