Continuous Doubly Constrained Batch Reinforcement Learning
This addresses the high cost of exploration in real-world RL applications by enabling effective policy learning from fixed offline data, though it is incremental as it builds on existing batch RL methods.
The paper tackles the problem of batch reinforcement learning's reliance on offline datasets by proposing an algorithm that uses policy and value constraints to mitigate uncertainty and extrapolation issues, achieving favorable results on 32 continuous-action benchmarks.
Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. This leads to particularly severe extrapolation when our candidate policies diverge from one that generated the data. We propose to mitigate this issue via two straightforward penalties: a policy-constraint to reduce this divergence and a value-constraint that discourages overly optimistic estimates. Over a comprehensive set of 32 continuous-action batch RL benchmarks, our approach compares favorably to state-of-the-art methods, regardless of how the offline data were collected.