We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). The algorithm addresses several limitations of existing techniques that do not take the information asymmetry between the expert and the learner into account. First, it adopts causal entropy as the measure of the likelihood of the expert demonstrations as opposed to entropy in most existing IRL techniques, and avoids a common source of algorithmic complexity. Second, it incorporates task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations and may reduce the information asymmetry. Nevertheless, the resulting formulation is still nonconvex due to the intrinsic nonconvexity of the so-called forward problem, i.e., computing an optimal policy given a reward function, in POMDPs. We address this nonconvexity through sequential convex programming and introduce several extensions to solve the forward problem in a scalable manner.This scalability allows computing policies that incorporate memory at the expense of added computational cost yet also outperform memoryless policies. We demonstrate that, even with severely limited data, the algorithm learns reward functions and policies that satisfy the task and induce a similar behavior to the expert by leveraging the side information and incorporating memory into the policy.
more »
« less
This content will become publicly available on May 30, 2024
LTL-Based Non-Markovian Inverse Reinforcement Learning
The successes of reinforcement learning in recent years are underpinned by the characterization of suitable reward functions. However, in settings where such rewards are non-intuitive, difficult to define, or otherwise error-prone in their definition, it is useful to instead learn the reward signal from expert demonstrations. This is the crux of inverse reinforcement learning (IRL). While eliciting learning requirements in the form of scalar reward signals has been shown to be effective, such representations lack explainability and lead to opaque learning. We aim to mitigate this situation by presenting a novel IRL method for eliciting declarative learning requirements in the form of a popular formal logic---Linear Temporal Logic (LTL)---from a set of traces given by the expert policy.
more »
« less
- Award ID(s):
- 2146563
- NSF-PAR ID:
- 10419684
- Date Published:
- Journal Name:
- Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)
- Page Range / eLocation ID:
- 2857–2859
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cancer screening is a large, population-based intervention that would benefit from tools enabling individually-tailored decision making to decrease unintended consequences such as overdiagnosis. The heterogeneity of cancer screening participants advocates the need for more personalized approaches. Partially observable Markov decision processes (POMDPs) can be used to suggest optimal, individualized screening policies. However, determining an appropriate reward function can be challenging. Here, we propose the use of inverse reinforcement learning (IRL) to form rewards functions for lung and breast cancer screening POMDP models. Using data from the National Lung Screening Trial and our institution's breast screening registry, we developed two POMDP models with corresponding reward functions. Specifically, the maximum entropy (MaxEnt) IRL algorithm with an adaptive step size was used to learn rewards more efficiently; and combined with a multiplicative model to learn state-action pair rewards in the POMDP. The lung and breast cancer screening models were evaluated based on their ability to recommend appropriate screening decisions before the diagnosis of cancer. Results are comparable with experts' decisions. The lung POMDP demonstrated an improved performance in terms of recall and false positive rate in the second screening and post-screening stages. Precision (0.02-0.05) was comparable to experts' (0.02-0.06). The breast POMDP has excellent recall (0.97-1.00), matching the physicians and a satisfactory false positive rate (<0.03). The reward functions learned with the MaxEnt IRL algorithm, when combined with POMDP models in lung and breast cancer screening, demonstrate performance comparable to experts.more » « less
-
This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments. The objective is to infer a cost function that explains expert-demonstrated navigation behavior while relying only on the observations and state-control trajectory used by the expert. We develop a cost function representation composed of two parts: a probabilistic occupancy encoder, with recurrent dependence on the observation sequence, and a cost encoder, defined over the occupancy features. The representation parameters are optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder. Such differentiation is typically computed by dynamic programming through the value function over the whole state space. We observe that this is inefficient in large partially observable environments because most states are unexplored. Instead, we rely on a closed-form subgradient of the cost-to-go obtained only over a subset of promising states via an efficient motion-planning algorithm such as A* or RRT. Our experiments show that our model exceeds the accuracy of baseline IRL algorithms in robot navigation tasks, while substantially improving the efficiency of training and test-time inference.more » « less
-
null (Ed.)Interactive reinforcement learning (IRL) agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that’s either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known IRL technique. Usually policy shaping employs a human feedback policy to help an agent to learn more about how to achieve its goal. In our case, we replace this human feedback policy with policy generated based on natural language advice. We aim to inspect if the generated natural language reasoning provides support to a deep RL agent to decide its actions successfully in any given environment. So, we design our model with three networks: first one is the experience driven, next is the advice generator and third one is the advice driven. While the experience driven RL agent chooses its actions being influenced by the environmental reward, the advice driven neural network with generated feedback by the advice generator for any new state selects its actions to assist the RL agent to better policy shaping.more » « less
-
In large agent-based models, it is difficult to identify the correlate system-level dynamics with individuallevel attributes. In this paper, we use inverse reinforcement learning to estimate compact representations of behaviors in large-scale pandemic simulations in the form of reward functions. We illustrate the capacity and performance of these representations identifying agent-level attributes that correlate with the emerging dynamics of large-scale multi-agent systems. Our experiments use BESSIE, an ABM for COVID-like epidemic processes, where agents make sequential decisions (e.g., use PPE/refrain from activities) based on observations (e.g., number of mask wearing people) collected when visiting locations to conduct their activities. The IRL-based reformulations of simulation outputs perform significantly better in classification of agent-level attributes than direct classification of decision trajectories and are thus more capable of determining agent-level attributes with definitive role in the collective behavior of the system. We anticipate that this IRL-based approach is broadly applicable to general ABMs.more » « less
