An official website of the United States government
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
Experiment Planning with Function Approximation
We study the problem of experiment planning with function approximation in contextual bandit problems. In settings where there is a significant overhead to deploying adaptive algorithms—for example, when the execution of the data collection policies is required to be distributed, or a human in the loop is needed to implement these policies—producing in advance a set of policies for data collection is paramount. We study the setting where a large dataset of contexts but not rewards is available and may be used by the learner to design an effective data collection strategy. Although when rewards are linear this problem has been well studied [53], results are still missing for more complex reward models. In this work we propose two experiment planning strategies compatible with function approximation. The first is an eluder planning and sampling procedure that can recover optimality guarantees depending on the eluder dimension [42] of the reward function class. For the second, we show that a uniform sampler achieves competitive optimality rates in the setting where the number of actions is small. We finalize our results introducing a statistical gap fleshing out the fundamental differences between planning and adaptive learning and provide results for planning with model selection.
more »
« less
- Award ID(s):
- 2112926
- PAR ID:
- 10577820
- Publisher / Repository:
- Neural Information Processing Systems
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
We consider the bandit problem of selecting K out of N arms at each time step. The joint reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing among all possible combinations, making the action space large. To simplify the problem, existing works on combinatorial bandits typically assume feedback as a linear function of individual rewards. In this paper, we prove the lower bound for top-K subset selection with bandit feedback with possibly correlated rewards. We present a novel algorithm for the combinatorial setting without using individual arm feedback or requiring linearity of the reward function. Additionally, our algorithm works on correlated rewards of individual arms. Our algorithm, aDaptive Accept RejecT (DART), sequentially finds good arms and eliminates bad arms based on confidence bounds. DART is computationally efficient and uses storage linear in N. Further, DART achieves a regret bound of Õ(K√KNT) for a time horizon T, which matches the lower bound in bandit feedback up to a factor of √log 2NT. When applied to the problem of cross-selling optimization and maximizing the mean of individual rewards, the performance of the proposed algorithm surpasses that of state-of-the-art algorithms. We also show that DART significantly outperforms existing methods for both linear and non-linear joint reward environments.more » « less
-
Due to information asymmetry, finding optimal policies for Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) is hard with the complexity growing doubly exponentially in the horizon length. The challenge increases greatly in the multi-agent reinforcement learning (MARL) setting where the transition probabilities, observation kernel, and reward function are unknown. Here, we develop a general compression framework with approximate common and private state representations, based on which decentralized policies can be constructed. We derive the optimality gap of executing dynamic programming (DP) with the approximate states in terms of the approximation error parameters and the remaining time steps. When the compression is exact (no error), the resulting DP is equivalent to the one in existing work. Our general framework generalizes a number of methods proposed in the literature. The results shed light on designing practically useful deep-MARL network structures under the "centralized learning distributed execution" scheme.more » « less
-
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a po- tentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communi- cation, heterogeneity in the reward functions and transition kernels of the agents’ MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the ex- tent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
