Contrastive Difference Predictive Coding
This work addresses the challenge of data inefficiency in learning long-term dependencies for time-series prediction, specifically for goal-conditioned reinforcement learning, offering an incremental improvement over existing contrastive methods.
The paper tackles the problem of learning representations for predicting future events in time-series data, particularly in goal-conditioned reinforcement learning, by introducing a temporal difference version of contrastive predictive coding that stitches together pieces of different time series to reduce data requirements. The result shows a 2× median improvement in success rates compared to prior RL methods, with 20× more sample efficiency than the successor representation and 1500× more than standard contrastive predictive coding in tabular settings.
Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the future. While prior methods have used contrastive predictive coding to model time series data, learning representations that encode long-term dependencies usually requires large amounts of data. In this paper, we introduce a temporal difference version of contrastive predictive coding that stitches together pieces of different time series data to decrease the amount of data required to learn predictions of future events. We apply this representation learning method to derive an off-policy algorithm for goal-conditioned RL. Experiments demonstrate that, compared with prior RL methods, ours achieves $2 \times$ median improvement in success rates and can better cope with stochastic environments. In tabular settings, we show that our method is about $20 \times$ more sample efficient than the successor representation and $1500 \times$ more sample efficient than the standard (Monte Carlo) version of contrastive predictive coding.