Designing reward functions is a difficult task in AI and robotics. The complex task of directly specifying all the desirable behaviors a robot needs to optimize often proves challenging for humans. A popular solution is to learn reward functions using expert demonstrations. This approach, however, is fraught with many challenges. Some methods require heavily structured models, for example, reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that may necessitate tremendous amounts of data. Moreover, it is difficult for humans to provide demonstrations on robots with high degrees of freedom, or even quantifying reward values for given trajectories. To address these challenges, we present a preference-based learning approach, where human feedback is in the form of comparisons between trajectories. We do not assume highly constrained structures on the reward function. Instead, we employ a Gaussian process to model the reward function and propose a mathematical formulation to actively fit the model using only human preferences. Our approach enables us to tackle both inflexibility and data-inefficiency problems within a preference-based learning framework. We further analyze our algorithm in comparison to several baselines on reward optimization, where the goal is to find the optimal robot trajectory in a data-efficient way instead of learning the reward function for every possible trajectory. Our results in three different simulation experiments and a user study show our approach can efficiently learn expressive reward functions for robotic tasks, and outperform the baselines in both reward learning and reward optimization.
Generating reward structures on a parameterized distribution of dynamics tasks
In order to make lifelike, versatile learning adaptive in the artificial domain, one needs a very diverse set of behaviors to learn. We propose a parameterized distribution of classic control-style tasks with minimal information shared between tasks. We discuss what makes a task trivial and offer a basic metric, time in convergence, that measures triviality. We then investigate analytic and empirical approaches to generating reward structures for tasks based on their dynamics in order to minimize triviality. Contrary to our expectations, populations evolved on reward structures that incentivized the most stable locations in state space spend the least time in convergence as we have defined it, because of the outsized importance our metric assigns to behavior fine-tuning in these contexts. This work paves the way towards an understanding of which task distributions enable the development of learning.
more »
« less
- Award ID(s):
- 1845322
- NSF-PAR ID:
- 10286536
- Editor(s):
- Cejkova, Jitka; Holler, Silvia; Soros, Lisa; Witkowski, Olaf
- Date Published:
- Journal Name:
- Artificial Life Conference Proceedings
- Volume:
- Alife 2021
- Issue:
- 2021
- Page Range / eLocation ID:
- 118-127
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified framework towards optimal learning for several well-motivated offline tasks. Uniform OPE supΠ|Qπ−Q̂ π|<ϵ is a stronger measure than the point-wise OPE and ensures offline learning when Π contains all policies (the global class). In this paper, we establish an Ω(H2S/dmϵ2) lower bound (over model-based family) for the global uniform OPE and our main result establishes an upper bound of Õ (H2/dmϵ2) for the \emph{local} uniform convergence that applies to all \emph{near-empirically optimal} policies for the MDPs with \emph{stationary} transition. Here dm is the minimal marginal state-action probability. Critically, the highlight in achieving the optimal rate Õ (H2/dmϵ2) is our design of \emph{singleton absorbing MDP}, which is a new sharp analysis tool that works with the model-based approach. We generalize such a model-based framework to the new settings: offline task-agnostic and the offline reward-free with optimal complexity Õ (H2log(K)/dmϵ2) (K is the number of tasks) and Õ (H2S/dmϵ2) respectively. These results provide a unified solution for simultaneously solving different offline RL problems.more » « less
-
more » « less
Applying reinforcement learning (RL) to sparse reward domains is notoriously challenging due to insufficient guiding signals. Common RL techniques for addressing such domains include (1) learning from demonstrations and (2) curriculum learning. While these two approaches have been studied in detail, they have rarely been considered together. This paper aims to do so by introducing a principled task-phasing approach that uses demonstrations to automatically generate a curriculum sequence. Using inverse RL from (suboptimal) demonstrations we define a simple initial task. Our task phasing approach then provides a framework to gradually increase the complexity of the task all the way to the target task, while retuning the RL agent in each phasing iteration. Two approaches for phasing are considered: (1) gradually increasing the proportion of time steps an RL agent is in control, and (2) phasing out a guiding informative reward function. We present conditions that guarantee the convergence of these approaches to an optimal policy. Experimental results on 3 sparse reward domains demonstrate that our task-phasing approaches outperform state-of-the-art approaches with respect to asymptotic performance.
-
Feature acquisition in predictive modeling is an important task in many practical applications. For example, in patient health prediction, we do not fully observe their personal features and need to dynamically select features to acquire. Our goal is to acquire a small subset of features that maximize prediction performance. Recently, some works reformulated feature acquisition as a Markov decision process and applied reinforcement learning (RL) algorithms, where the reward reflects both prediction performance and feature acquisition cost. However, RL algorithms only use zeroth-order information on the reward, which leads to slow empirical convergence, especially when there are many actions (number of features) to consider. For predictive modeling, it is possible to use first-order information on the reward, i.e., gradients, since we are often given an already collected dataset. Therefore, we propose differentiable feature acquisition (DiFA), which uses a differentiable representation of the feature selection policy to enable gradients to flow from the prediction loss to the policy parameters. We conduct extensive experiments on various real-world datasets and show that DiFA significantly outperforms existing feature acquisition methods when the number of features is large.more » « less
-
null (Ed.)Communication between human and mobile agents is getting increasingly important as such agents are widely deployed in our daily lives. Vision-and-Dialogue Navigation is one of the tasks that evaluate the agent’s ability to interact with humans for assistance and navigate based on natural language responses. In this paper, we explore the Navigation from Dialogue History (NDH) task, which is based on the Cooperative Vision-and-Dialogue Navigation (CVDN) dataset, and present a state-of-the-art model which is built upon Vision-Language transformers. However, despite achieving competitive performance, we find that the agent in the NDH task is not evaluated appropriately by the primary metric – Goal Progress. By analyzing the performance mismatch between Goal Progress and other metrics (e.g., normalized Dynamic Time Warping) from our state-of-the-art model, we show that NDH’s sub-path based task setup (i.e., navigating partial trajectory based on its correspondent subset of the full dialogue) does not provide the agent with enough supervision signal towards the goal region. Therefore, we propose a new task setup called NDH-Full which takes the full dialogue and the whole navigation path as one instance. We present a strong baseline model and show initial results on this new task. We further describe several approaches that we try, in order to improve the model performance (based on curriculum learning, pre-training, and data-augmentation), suggesting potential useful training methods on this new NDH-Full task.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1162/isal_a_00466
