More Like this

1. Decision Making in Non-Stationary Environments with Policy-Augmented Monte Carlo Tree Search

   Pettet, Geoffrey; Mukhopadhyay, Ayan; Dubey, Abhishek (January 2022, The Multi-disciplinary Conference on Reinforcement Learning and Decision Making)

   Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (RL), a popular approach for DMU problems, learns a policy by interacting with a model of the environment offline. Unfortunately, if the environment changes the policy can become stale and take sub-optimal actions, and relearning the policy for the updated environment takes time and computational effort. An alternative is online planning approaches such as Monte Carlo Tree Search (MCTS), which perform their computation at decision time. Given the current environment, MCTS plans using high-fidelity models to determine promising action trajectories. These models can be updated as soon as environmental changes are detected to immediately incorporate them into decision making. However, MCTS’s convergence can be slow for domains with large state-action spaces. In this paper, we present a novel hybrid decision-making approach that combines the strengths of RL and planning while mitigating their weaknesses. Our approach, called Policy Augmented MCTS (PA-MCTS), integrates a policy’s actin-value estimates into MCTS, using the estimates to seed the action trajectories favored by the search. We hypothesize that PA-MCTS will converge more quickly than standard MCTS while making better decisions than the policy can make on its own when faced with nonstationary environments. We test our hypothesis by comparing PA-MCTS with pure MCTS and an RL agent applied to the classical CartPole environment. We find that PC-MCTS can achieve higher cumulative rewards than the policy in isolation under several environmental shifts while converging in significantly fewer iterations than pure MCTS. 

   more » « less
2. Efficient Duple Perturbation Robustness in Low-rank MDPs

   Hu, Yang; Ma, Haitong; Li, Na; Dai, Bo (June 2025, PMLR)

   Ozay, Necmiye; Balzano, Laura; Panagou, Dimitra; Abate, Alessandro (Ed.)

   The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from computation issues that obstruct their real-world implementation. In this paper, we consider MDPs with low-rank structures, where the transition kernel can be written as a linear product of feature map and factors. We introduce *duple perturbation* robustness, i.e. perturbation on both the feature map and the factors, via a novel characterization of (𝜉,𝜂) -ambiguity sets featuring computational efficiency. Our novel low-rank robust MDP formulation is compatible with the low-rank function representation view, and therefore, is naturally applicable to practical RL problems with large or even continuous state-action spaces. Meanwhile, it also gives rise to a provably efficient and practical algorithm with theoretical convergence rate guarantee. Lastly, the robustness of our proposed approach is justified by numerical experiments, including classical control tasks with continuous state-action spaces. 

   more » « less
3. Learning Bellman Complete Representations for Offline Policy Evaluation

   Jonathan Chang, Kaiwen Wang (January 2022, Proceedings of the 39th International Conference on Machine Learning)

   We study representation learning for Offline Reinforcement Learning (RL), focusing on the important task of Offline Policy Evaluation (OPE). Recent work shows that, in contrast to supervised learning, realizability of the Q-function is not enough for learning it. Two sufficient conditions for sample-efficient OPE are Bellman completeness and coverage. Prior work often assumes that representations satisfying these conditions are given, with results being mostly theoretical in nature. In this work, we propose BCRL, which directly learns from data an approximately linear Bellman complete representation with good coverage. With this learned representation, we perform OPE using Least Square Policy Evaluation (LSPE) with linear functions in our learned representation. We present an end-to-end theoretical analysis, showing that our two-stage algorithm enjoys polynomial sample complexity provided some representation in the rich class considered is linear Bellman complete. Empirically, we extensively evaluate our algorithm on challenging, image-based continuous control tasks from the Deepmind Control Suite. We show our representation enables better OPE compared to previous representation learning methods developed for off-policy RL (e.g., CURL, SPR). BCRL achieve competitive OPE error with the state-of-the-art method Fitted Q-Evaluation (FQE), and beats FQE when evaluating beyond the initial state distribution. Our ablations show that both linear Bellman complete and coverage components of our method are crucial. 

   more » « less
4. Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

   Shi, Laixi; Li, Gen; Wei, Yuting; Chen, Yuxin; Chi, Yuejie (January 2022, Proceedings of the 39th International Conference on Machine Learning)

   Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle of pessimism has been recently introduced to mitigate high bias of the estimated values. While pessimistic variants of model-based algorithms (e.g., value iteration with lower confidence bounds) have been theoretically investigated, their model-free counterparts — which do not require explicit model estimation — have not been adequately studied, especially in terms of sample efficiency. To address this inadequacy, we study a pessimistic variant of Q-learning in the context of finite-horizon Markov decision processes, and characterize its sample complexity under the single-policy concentrability assumption which does not require the full coverage of the state-action space. In addition, a variance-reduced pessimistic Q-learning algorithm is proposed to achieve near-optimal sample complexity. Altogether, this work highlights the efficiency of model-free algorithms in offline RL when used in conjunction with pessimism and variance reduction. 

   more » « less
5. Learning Value Functions from Undirected State-only Experience

   Chang, Matthew; Gupta, Arjun; Gupta, Saurabh (April 2022, International Conference on Learning Representations (ICLR))

   Abstract: This paper tackles the problem of learning value functions from undirected state-only experience (state transitions without action labels i.e. (s,s’,r) tuples). We first theoretically characterize the applicability of Q-learning in this setting. We show that tabular Q-learning in discrete Markov decision processes (MDPs) learns the same value function under any arbitrary refinement of the action space. This theoretical result motivates the design of Latent Action Q-learning or LAQ, an offline RL method that can learn effective value functions from state-only experience. Latent Action Q-learning (LAQ) learns value functions using Q-learning on discrete latent actions obtained through a latent-variable future prediction model. We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions. Value functions learned using LAQ lead to sample efficient acquisition of goal-directed behavior, can be used with domain-specific low-level controllers, and facilitate transfer across embodiments. Our experiments in 5 environments ranging from 2D grid world to 3D visual navigation in realistic environments demonstrate the benefits of LAQ over simpler alternatives, imitation learning oracles, and competing methods. 

   more » « less