Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction

Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the application of offline RL to the safe and efficient control of an exothermic polymerisation continuous stirred-tank reactor. We introduce a Gymnasium-compatible simulation environment that captures the reactor's nonlinear dynamics, including reaction kinetics, energy balances, and operational constraints. The environment supports three industrially relevant scenarios: startup, grade change down, and grade change up. It also includes reproducible offline datasets generated from proportional-integral controllers with randomised tunings, providing a benchmark for evaluating offline RL algorithms in realistic process control tasks. We assess behaviour cloning and implicit Q-learning as baseline algorithms, highlighting the challenges offline agents face, including steady-state offsets and degraded performance near setpoints. To address these issues, we propose a novel deployment-time safety layer that performs gradient-based action correction using input convex neural networks (PICNNs) as learned cost models. The PICNN enables real-time, differentiable correction of policy actions by descending a convex, state-conditioned cost surface, without requiring retraining or environment interaction. Experimental results show that offline RL, particularly when combined with convex action correction, can outperform traditional control approaches and maintain stability across all scenarios. These findings demonstrate the feasibility of integrating offline RL with interpretable and safety-aware corrections for high-stakes chemical process control, and lay the groundwork for more reliable data-driven automation in industrial systems.

Deep Reinforcement Learning for Gas Trading

Deep Reinforcement Learning (Deep RL) has been explored for a number of applications in finance and stock trading. In this paper, we present a practical implementation of Deep RL for trading natural gas futures contracts. The Sharpe Ratio obtained exceeds benchmarks given by trend following and mean reversion strategies as well as results reported in literature. Moreover, we propose a simple but effective ensemble learning scheme for trading, which significantly improves performance through enhanced model stability and robustness as well as lower turnover and hence lower transaction cost. We discuss the resulting Deep RL strategy in terms of model explainability, trading frequency and risk measures.

Deep Reinforcement Learning for Power Trading

The Dutch power market includes a day-ahead market and an auction-like intraday balancing market. The varying supply and demand of power and its uncertainty induces an imbalance, which causes differing power prices in these two markets and creates an opportunity for arbitrage. In this paper, we present collaborative dual-agent reinforcement learning (RL) for bi-level simulation and optimization of European power arbitrage trading. Moreover, we propose two novel practical implementations specifically addressing the electricity power market. Leveraging the concept of imitation learning, the RL agent's reward is reformed by taking into account prior domain knowledge results in better convergence during training and, moreover, improves and generalizes performance. In addition, tranching of orders improves the bidding success rate and significantly raises the P&L. We show that each method contributes significantly to the overall performance uplifting, and the integrated methodology achieves about three-fold improvement in cumulative P&L over the original agent, as well as outperforms the highest benchmark policy by around 50% while exhibits efficient computational performance.