An official website of the United States government
Over the past decade, deep reinforcement learning (RL) techniques have significantly advanced robotic systems. However, due to the complex architectures of neural network models, ensuring their trustworthiness is a considerable challenge. Programmatic reinforcement learning has surfaced as a promising approach. Nonetheless, synthesizing robot-control programs remains challenging. Existing methods rely on domain-specific languages (DSLs) populated with user-defined state abstraction predicates and a library of low-level controllers as abstract actions to boot synthesis, which is impractical in unknown environments that lack such predefined components. To address this limitation, we introduce RoboScribe, a novel abstraction refinement-guided program synthesis framework that automatically derives robot state and action abstractions from raw, unsegmented task demonstrations in high-dimensional, continuous spaces. It iteratively enriches and refines an initially coarse abstraction until it generates a task-solving program over the abstracted robot environment. RoboScribe is effective in synthesizing iterative programs by inferring recurring subroutines directly from the robot’s raw, continuous state and action spaces, without needing predefined abstractions. Experimental results show that RoboScribe programs inductively generalize to long-horizon robot tasks involving arbitrary numbers of objects, outperforming baseline methods in terms of both interpretability and efficiency.
more »
« less
Reward-Guided Synthesis of Intelligent Agents with Control Structures
Deep reinforcement learning (RL) has led to encouraging successes in numerous challenging robotics applications. However, the lack of inductive biases to support logic deduction and generalization in the representation of a deep RL model causes it less effective in exploring complex long-horizon robot-control tasks with sparse reward signals. Existing program synthesis algorithms for RL problems inherit the same limitation, as they either adapt conventional RL algorithms to guide program search or synthesize robot-control programs to imitate an RL model. We propose ReGuS, a reward-guided synthesis paradigm, to unlock the potential of program synthesis to overcome the exploration challenges. We develop a novel hierarchical synthesis algorithm with decomposed search space for loops, on-demand synthesis of conditional statements, and curriculum synthesis for procedure calls, to effectively compress the exploration space for long-horizon, multi-stage, and procedural robot-control tasks that are difficult to address by conventional RL techniques. Experiment results demonstrate that ReGuS significantly outperforms state-of-the-art RL algorithms and standard program synthesis baselines on challenging robot tasks including autonomous driving, locomotion control, and object manipulation. CCS Concepts: •Software and its engineering → Automatic programming.
more »
« less
- Award ID(s):
- 2124155
- PAR ID:
- 10612732
- Publisher / Repository:
- Association for Computing Machinery (ACM)
- Date Published:
- Journal Name:
- Proceedings of the ACM on Programming Languages
- Volume:
- 8
- Issue:
- PLDI
- ISSN:
- 2475-1421
- Format(s):
- Medium: X Size: p. 1730-1754
- Size(s):
- p. 1730-1754
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep reinforcement learning (RL) has led to encouraging successes in many challenging control tasks. However, a deep RL model lacks interpretability due to the difficulty of identifying how the model's control logic relates to its network structure. Programmatic policies structured in more interpretable representations emerge as a promising solution. Yet two shortcomings remain: First, synthesizing programmatic policies requires optimizing over the discrete and non-differentiable search space of program architectures. Previous works are suboptimal because they only enumerate program architectures greedily guided by a pretrained RL oracle. Second, these works do not exploit compositionality, an important programming concept, to reuse and compose primitive functions to form a complex function for new tasks. Our first contribution is a programmatically interpretable RL framework that conducts program architecture search on top of a continuous relaxation of the architecture space defined by programming language grammar rules. Our algorithm allows policy architectures to be learned with policy parameters via bilevel optimization using efficient policy-gradient methods, and thus does not require a pretrained oracle. Our second contribution is improving programmatic policies to support compositionality by integrating primitive functions learned to grasp task-agnostic skills as a composite program to solve novel RL problems. Experiment results demonstrate that our algorithm excels in discovering optimal programmatic policies that are highly interpretable.more » « less
-
Abstract The ability to reuse trained models in Reinforcement Learning (RL) holds substantial practical value in particular for complex tasks. While model reusability is widely studied for supervised models in data management, to the best of our knowledge, this is the first ever principled study that is proposed for RL. To capture trained policies, we develop a framework based on an expressive and lossless graph data model that accommodates Temporal Difference Learning and Deep-RL based RL algorithms. Our framework is able to capture arbitrary reward functions that can be composed at inference time. The framework comes with theoretical guarantees and shows that it yields the same result as policies trained from scratch. We design a parameterized algorithm that strikes a balance between efficiency and quality w.r.t cumulative reward. Our experiments with two common RL tasks (query refinement and robot movement) corroborate our theory and show the effectiveness and efficiency of our algorithms.more » « less
-
Despite the potential of reinforcement learning (RL) for building general-purpose robotic systems, training RL agents to solve robotics tasks still remains challenging due to the difficulty of exploration in purely continuous action spaces. Addressing this problem is an active area of research with the majority of focus on improving RL methods via better optimization or more efficient exploration. An alternate but important component to consider improving is the interface of the RL algorithm with the robot. In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. These parameterized primitives are expressive, simple to implement, enable efficient exploration and can be transferred across robots, tasks and environments. We perform a thorough empirical study across challenging tasks in three distinct domains with image input and a sparse terminal reward. We find that our simple change to the action interface substantially improves both the learning efficiency and task performance irrespective of the underlying RL algorithm, significantly outperforming prior methods which learn skills from offline expert data. Code and videos at https://mihdalal.github.io/raps/more » « less
-
null (Ed.)A promising approach to solving challenging long-horizon tasks has been to extract behavior priors (skills) by fitting generative models to large offline datasets of demonstrations. However, such generative models inherit the biases of the underlying data and result in poor and unusable skills when trained on imperfect demonstration data. To better align skill extraction with human intent we present Skill Preferences (SkiP), an algorithm that learns a model over human preferences and uses it to extract human-aligned skills from offline data. After extracting human-preferred skills, SkiP also utilizes human feedback to solve downstream tasks with RL. We show that SkiP enables a simulated kitchen robot to solve complex multi-step manipulation tasks and substantially outperforms prior leading RL algorithms with human preferences as well as leading skill extraction algorithms without human preferences.more » « less
