Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning

• URL: http://arxiv.org/abs/2209.10974v1
• Date: Thu, 22 Sep 2022 12:50:00 GMT
• Title: Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning
• Authors: Paul Rolland, Luca Viano, Norman Schuerhoff, Boris Nikolov, Volkan Cevher
• Abstract summary: Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment. Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior.
• Score: 39.632717308147825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is well known that, in general, various reward functions can lead to the same optimal policy, and hence, IRL is ill-defined. However, (Cao et al., 2021) showed that, if we observe two or more experts with different discount factors or acting in different environments, the reward function can under certain conditions be identified up to a constant. This work starts by showing an equivalent identifiability statement from multiple experts in tabular MDPs based on a rank condition, which is easily verifiable and is shown to be also necessary. We then extend our result to various different scenarios, i.e., we characterize reward identifiability in the case where the reward function can be represented as a linear combination of given features, making it more interpretable, or when we have access to approximate transition matrices. Even when the reward is not identifiable, we provide conditions characterizing when data on multiple experts in a given environment allows to generalize and train an optimal agent in a new environment. Our theoretical results on reward identifiability and generalizability are validated in various numerical experiments.

Related papers

• On Multi-Agent Inverse Reinforcement Learning [8.284137254112848]
  We extend the Inverse Reinforcement Learning (IRL) framework to the multi-agent setting, assuming to observe agents who are following Nash Equilibrium (NE) policies. We provide an explicit characterization of the feasible reward set and analyze how errors in estimating the transition dynamics and expert behavior impact the recovered rewards.
  arXiv  Detail & Related papers  (2024-11-22T16:31:36Z)
• Inverse Reinforcement Learning with Sub-optimal Experts [56.553106680769474]
  We study the theoretical properties of the class of reward functions that are compatible with a given set of experts. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. We analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.
  arXiv  Detail & Related papers  (2024-01-08T12:39:25Z)
• Invariance in Policy Optimisation and Partial Identifiability in Reward Learning [67.4640841144101]
  We characterise the partial identifiability of the reward function given popular reward learning data sources. We also analyse the impact of this partial identifiability for several downstream tasks, such as policy optimisation.
  arXiv  Detail & Related papers  (2022-03-14T20:19:15Z)
• On the Expressivity of Markov Reward [89.96685777114456]
  This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of "task" that might be desirable: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories.
  arXiv  Detail & Related papers  (2021-11-01T12:12:16Z)
• Identifiability in inverse reinforcement learning [0.0]
  Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem. We provide a resolution to this non-identifiability for problems with entropy regularization.
  arXiv  Detail & Related papers  (2021-06-07T10:35:52Z)
• Reward function shape exploration in adversarial imitation learning: an empirical study [9.817069267241575]
  In adversarial imitation learning algorithms (AILs), no true rewards are obtained from the environment for learning the strategy. We design several representative reward function shapes and compare their performances by large-scale experiments.
  arXiv  Detail & Related papers  (2021-04-14T08:21:49Z)
• Information Directed Reward Learning for Reinforcement Learning [64.33774245655401]
  We learn a model of the reward function that allows standard RL algorithms to achieve high expected return with as few expert queries as possible. In contrast to prior active reward learning methods designed for specific types of queries, IDRL naturally accommodates different query types. We support our findings with extensive evaluations in multiple environments and with different types of queries.
  arXiv  Detail & Related papers  (2021-02-24T18:46:42Z)
• Understanding Learned Reward Functions [6.714172005695389]
  We investigate techniques for interpreting learned reward functions. In particular, we apply saliency methods to identify failure modes and predict the robustness of reward functions. We find that learned reward functions often implement surprising algorithms that rely on contingent aspects of the environment.
  arXiv  Detail & Related papers  (2020-12-10T18:19:48Z)
• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning [22.242379207077217]
  We show how to show the reward function's code to the RL agent so it can exploit the function's internal structure to learn optimal policies. First, we propose reward machines, a type of finite state machine that supports the specification of reward functions. We then describe different methodologies to exploit this structure to support learning, including automated reward shaping, task decomposition, and counterfactual reasoning with off-policy learning.
  arXiv  Detail & Related papers  (2020-10-06T00:10:16Z)
• Maximizing Information Gain in Partially Observable Environments via Prediction Reward [64.24528565312463]
  This paper tackles the challenge of using belief-based rewards for a deep RL agent. We derive the exact error between negative entropy and the expected prediction reward. This insight provides theoretical motivation for several fields using prediction rewards.
  arXiv  Detail & Related papers  (2020-05-11T08:13:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.