A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an intuitive but sparse reward function that only indicates whether the task is completed partially or fully. However, the lack of carefully designed, fine grain feedback implies that most existing RL algorithms fail to learn an acceptable policy in a reasonable time frame. This is because of the large number of exploration actions that the policy has to perform before it gets any useful feedback that it can learn from. In this work, we address this challenging problem by developing an algorithm that exploits the offline demonstration data generated by a sub-optimal behavior policy for faster and efficient online RL in such sparse reward settings. The proposed algorithm, which we call the Learning Online with Guidance Offline (LOGO) algorithm, merges a policy improvement step with an additional policy guidance step by using the offline demonstration data. The key idea is that by obtaining guidance from - not imitating - the offline data, LOGO orients its policy in the manner of the sub-optimal policy, while yet being able to learn beyond and approach optimality. We provide a theoretical analysis of our algorithm, and provide a lower bound on the performance improvement in each learning episode. We also extend our algorithm to the even more challenging incomplete observation setting, where the demonstration data contains only a censored version of the true state observation. We demonstrate the superior performance of our algorithm over state-of-the-art approaches on a number of benchmark environments with sparse rewards and censored state. Further, we demonstrate the value of our approach via implementing LOGO on a mobile robot for trajectory tracking and obstacle avoidance, where it shows excellent performance.
more »
« less
This content will become publicly available on March 25, 2025
Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption
We study offline reinforcement learning (RL) with heavy-tailed reward distribution and data corruption: (i) Moving beyond subGaussian reward distribution, we allow the rewards to have infinite variances; (ii) We allow corruptions where an attacker can arbitrarily modify a small fraction of the rewards and transitions in the dataset. We first derive a sufficient optimality condition for generalized Pessimistic Value Iteration (PEVI), which allows various estimators with proper confidence bounds and can be applied to multiple learning settings. In order to handle the data corruption and heavy-tailed reward setting, we prove that the trimmed-mean estimation achieves the minimax optimal error rate for robust mean estimation under heavy-tailed distributions. In the PEVI algorithm, we plug in the trimmed mean estimation and the confidence bound to solve the robust offline RL problem. Standard analysis reveals that data corruption induces a bias term in the suboptimality gap, which gives the false impression that any data corruption prevents optimal policy learning. By using the optimality condition for the generalized PEVI, we show that as long as the bias term is less than the ``action gap'', the policy returned by PEVI achieves the optimal value given sufficient data.
more » « less- Award ID(s):
- 1955997
- NSF-PAR ID:
- 10522284
- Publisher / Repository:
- AAAI Press
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 38
- Issue:
- 10
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 11416 to 11424
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as its optimal sample complexity, remain largely open even in basic settings such as \emph{tabular} Markov Decision Processes (MDPs). In this paper, we propose Off-Policy Double Variance Reduction (OPDVR), a new variance reduction based algorithm for offline RL. Our main result shows that OPDVR provably identifies an ϵ-optimal policy with O˜(H2/dmϵ2) episodes of offline data in the finite-horizon stationary transition setting, where H is the horizon length and dm is the minimal marginal state-action distribution induced by the behavior policy. This improves over the best known upper bound by a factor of H. Moreover, we establish an information-theoretic lower bound of Ω(H2/dmϵ2) which certifies that OPDVR is optimal up to logarithmic factors. Lastly, we show that OPDVR also achieves rate-optimal sample complexity under alternative settings such as the finite-horizon MDPs with non-stationary transitions and the infinite horizon MDPs with discounted rewards.more » « less
-
Reinforcement learning (RL) has demonstrated its superiority in solving sequential decision-making problems. However, heavy dependence on immediate reward feedback impedes the wide application of RL. On the other hand, imitation learning (IL) tackles RL without relying on environmental supervision by leveraging external demonstrations. In practice, however, collecting sufficient expert demonstrations can be prohibitively expensive, yet the quality of demonstrations typically limits the performance of the learning policy. To address a practical scenario, in this work, we propose Self-Adaptive Imitation Learning (SAIL), which, provided with a few demonstrations from a sub-optimal teacher, can perform well in RL tasks with extremely delayed rewards, where the only reward feedback is trajectory-wise ranking. SAIL bridges the advantages of IL and RL by interactively exploiting the demonstrations to catch up with the teacher and exploring the environment to yield demonstrations that surpass the teacher. Extensive empirical results show that not only does SAIL significantly improve the sample efficiency, but it also leads to higher asymptotic performance across different continuous control tasks, compared with the state-of-the-art.more » « less
-
more » « less
Offline reinforcement learning (offline RL) considers problems where learning is performed using only previously collected samples and is helpful for the settings in which collecting new data is costly or risky. In model-based offline RL, the learner performs estimation (or optimization) using a model constructed according to the empirical transition frequencies. We analyze the sample complexity of vanilla model-based offline RL with dependent samples in the infinite-horizon discounted-reward setting. In our setting, the samples obey the dynamics of the Markov decision process and, consequently, may have interdependencies. Under no assumption of independent samples, we provide a high-probability, polynomial sample complexity bound for vanilla model-based off-policy evaluation that requires partial or uniform coverage. We extend this result to the off-policy optimization under uniform coverage. As a comparison to the model-based approach, we analyze the sample complexity of off-policy evaluation with vanilla importance sampling in the infinite-horizon setting. Finally, we provide an estimator that outperforms the sample-mean estimator for almost deterministic dynamics that are prevalent in reinforcement learning.
-
Learning optimal policies in real-world domains with delayed rewards is a major challenge in Reinforcement Learning. We address the credit assignment problem by proposing a Gaussian Process (GP)-based immediate reward approximation algorithm and evaluate its effectiveness in 4 contexts where rewards can be delayed for long trajectories. In one GridWorld game and 8 Atari games, where immediate rewards are available, our results showed that on 7 out 9 games, the proposed GP inferred reward policy performed at least as well as the immediate reward policy and significantly outperformed the corresponding delayed reward policy. In e-learning and healthcare applications, we combined GP-inferred immediate rewards with offline Deep Q-Network (DQN) policy induction and showed that the GP-inferred reward policies outperformed the policies induced using delayed rewards in both real-world contexts.more » « less
