Skip to yearly menu bar Skip to main content


Oral 3 Track 1: Reinforcement Learning



Chat is not available.

Tue 2 May 1:00 - 1:10 PDT

In-Person Oral presentation / top 25% paper
Adversarial Diversity in Hanabi

Brandon Cui · Andrei Lupu · Samuel Sokota · Hengyuan Hu · David Wu · Jakob Foerster

Many Dec-POMDPs admit a qualitatively diverse set of ''reasonable'' joint policies, where reasonableness is indicated by symmetry equivariance, non-sabotaging behaviour and the graceful degradation of performance when paired with ad-hoc partners. Some of the work in diversity literature is concerned with generating these policies. Unfortunately, existing methods fail to produce teams of agents that are simultaneously diverse, high performing, and reasonable. In this work, we propose a novel approach, adversarial diversity (ADVERSITY), which is designed for turn-based Dec-POMDPs with public actions. ADVERSITY relies on off-belief learning to encourage reasonableness and skill, and on ''repulsive'' fictitious transitions to encourage diversity. We use this approach to generate new agents with distinct but reasonable play styles for the card game Hanabi and open-source our agents to be used for future research on (ad-hoc) coordination.

Tue 2 May 1:10 - 1:20 PDT

In-Person Oral presentation / top 5% paper
Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

Kuo-Hao Zeng · Luca Weihs · Roozbeh Mottaghi · Ali Farhadi

A common assumption when training embodied agents is that the impact of taking an action is stable; for instance, executing the ``move ahead'' action will always move the agent forward by a fixed distance, perhaps with some small amount of actuator-induced noise. This assumption is limiting; an agent may encounter settings that dramatically alter the impact of actions: a move ahead action on a wet floor may send the agent twice as far as it expects and using the same action with a broken wheel might transform the expected translation into a rotation. Instead of relying that the impact of an action stably reflects its pre-defined semantic meaning, we propose to model the impact of actions on-the-fly using latent embeddings. By combining these latent action embeddings with a novel, transformer-based, policy head, we design an Action Adaptive Policy (AAP). We evaluate our AAP on two challenging visual navigation tasks in the AI2-THOR and Habitat environments and show that our AAP is highly performant even when faced, at inference-time, with missing actions and, previously unseen, perturbed action spaces. Moreover, we observe significant improvement in robustness against these actions when evaluating in real-world scenarios.

Tue 2 May 1:20 - 1:30 PDT

In-Person Oral presentation / top 25% paper
Programmatically Grounded, Compositionally Generalizable Robotic Manipulation

Renhao Wang · Jiayuan Mao · Joy Hsu · Hang Zhao · Jiajun Wu · Yang Gao

Robots operating in the real world require both rich manipulation skills as well as the ability to semantically reason about when to apply those skills. Towards this goal, recent works have integrated semantic representations from large-scale pretrained vision-language (VL) models into manipulation models, imparting them with more general reasoning capabilities. However, we show that the conventional {\it pretraining-finetuning} pipeline for integrating such representations entangles the learning of domain-specific action information and domain-general visual information, leading to less data-efficient training and poor generalization to unseen objects and tasks. To this end, we propose \ours, a {\it modular} approach to better leverage pretrained VL models by exploiting the syntactic and semantic structures of language instructions. Our framework uses a semantic parser to recover an executable program, composed of functional modules grounded on vision and action across different modalities. Each functional module is realized as a combination of deterministic computation and learnable neural networks. Program execution produces parameters to general manipulation primitives for a robotic end-effector. The entire modular network can be trained with end-to-end imitation learning objectives. Experiments show that our model successfully disentangles action and perception, translating to improved zero-shot and compositional generalization in a variety of manipulation behaviors. Project webpage at: \url{}.

Tue 2 May 1:30 - 1:40 PDT

In-Person Oral presentation / top 5% paper
On the Sensitivity of Reward Inference to Misspecified Human Models

Joey Hong · Kush Bhatia · Anca Dragan

Inferring reward functions from human behavior is at the center of value alignment – aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of reward learning seems ill-fated, as we will never have perfect models of human behavior. On the other hand, if as our models improve, we can have a guarantee that reward accuracy also improves, this would show the benefit of more work on the modeling side. We study this question both theoretically and empirically. We do show that it is unfortunately possible to construct small adversarial biases in behavior that lead to arbitrarily large errors in the inferred reward. However, and arguably more importantly, we are also able to identify reasonable assumptions under which the reward inference error can be bounded linearly in the error in the human model. Finally, we verify our theoretical insights in discrete and continuous control tasks with simulated and human data.

Tue 2 May 1:40 - 1:50 PDT

In-Person Oral presentation / top 25% paper
Understanding and Adopting Rational Behavior by Bellman Score Estimation

Kuno Kim · Stefano Ermon

We are interested in solving a class of problems that seek to understand and adopt rational behavior from demonstrations. We may broadly classify these problems into four categories of reward identification, counterfactual analysis, behavior imitation, and behavior transfer. In this work, we make a key observation that knowing how changes in the underlying rewards affect the optimal behavior allows one to solve a variety of aforementioned problems. To a local approximation, this quantity is precisely captured by what we term the Bellman score, i.e gradient of log probabilities of the optimal policy with respect to the reward. We introduce the Bellman score operator which provably converges to the gradient of the infinite-horizon optimal Q-values with respect to the reward which can then be used to directly estimate the score. Guided by our theory, we derive a practical score-learning algorithm which can be used for score estimation in high-dimensional state-actions spaces. We show that score-learning can be used to reliably identify rewards, perform counterfactual predictions, achieve state-of-the-art behavior imitation, and transfer policies across environments.

Tue 2 May 1:50 - 2:00 PDT

In-Person Oral presentation / top 25% paper
SMART: Self-supervised Multi-task pretrAining with contRol Transformers

Yanchao Sun · shuang ma · Ratnesh Madaan · Rogerio Bonatti · Furong Huang · Ashish Kapoor

Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to sequential decision-making tasks, however, it is difficult to properly design such a pretraining approach that can cope with both high-dimensional perceptual information and the complexity of sequential control over long interaction horizons. The challenge becomes combinatorially more complex if we want to pretrain representations amenable to a large variety of tasks. To tackle this problem, in this work, we formulate a general pretraining-finetuning pipeline for sequential decision making, under which we propose a generic pretraining framework \textit{Self-supervised Multi-task pretrAining with contRol Transformer (SMART)}. By systematically investigating pretraining regimes, we carefully design a Control Transformer (CT) coupled with a novel control-centric pretraining objective in a self-supervised manner. SMART encourages the representation to capture the common essential information relevant to short-term control and long-term control, which is transferrable across tasks. We show by extensive experiments in DeepMind Control Suite that SMART significantly improves the learning efficiency among seen and unseen downstream tasks and domains under different learning scenarios including Imitation Learning (IL) and Reinforcement Learning (RL). Benefiting from the proposed control-centric objective, SMART is resilient to distribution shift between pretraining and finetuning, and even works well with low-quality pretraining datasets that are randomly collected. The codebase, pretrained models and datasets are provided at

Tue 2 May 2:00 - 2:10 PDT

In-Person Oral presentation / top 5% paper
Dichotomy of Control: Separating What You Can Control from What You Cannot

Sherry Yang · Dale Schuurmans · Pieter Abbeel · Ofir Nachum

Future- or return-conditioned supervised learning is an emerging paradigm for offline reinforcement learning (RL), in which the future outcome (i.e., return) associated with a sequence of actions in an offline dataset is used as input to a policy trained to imitate those same actions. While return-conditioning is at the heart of popular algorithms such as decision transformer (DT), these methods tend to perform poorly in highly stochastic environments, where an occasional high return associated with a sequence of actions may be due more to the randomness of the environment than to the actions themselves. Such situations can lead to a learned policy that is inconsistent with its conditioning inputs; i.e., using the policy – while conditioned on a specific desired return – to act in the environment can lead to a distribution of real returns that is wildly different than desired. In this work, we propose the dichotomy of control (DoC), a future-conditioned supervised learning framework that separates mechanisms within a policy’s control (actions) from those outside of a policy’s control (environment stochasticity). We achieve this by conditioning the policy on a latent variable representation of the future and designing a mutual information constraint that removes any future information from the latent variable that is only due to randomness of the environment. Theoretically, we show that DoC yields policies that are consistent with their conditioning inputs, ensuring that conditioning a learned policy on a desired high-return future outcome will correctly induce high-return behavior. Empirically, we show that DoC is able to achieve significantly better performance than DT on environments with highly stochastic rewards (e.g., Bandit) and transitions (e.g., FrozenLake).

Tue 2 May 2:10 - 2:20 PDT

In-Person Oral presentation / top 5% paper
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

Michał Zawalski · Michał Tyrolski · Konrad Czechowski · Tomasz Odrzygóźdź · Damian Stachura · Piotr Piękos · Yuhuai Wu · Łukasz Kuciński · Piotr Miłoś

Complex reasoning problems contain states that vary in the computational cost required to determine the right action plan. To take advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts the planning horizon. To this end, AdaSubS generates diverse sets of subgoals at different distances. A verification mechanism is employed to filter out unreachable subgoals swiftly, making it possible to focus on feasible further subgoals. In this way, AdaSubS benefits from the efficiency of planning with longer-term subgoals and the fine control with shorter-term ones, and thus scales well to difficult planning problems. We show that AdaSubS significantly surpasses hierarchical planning algorithms on three complex reasoning tasks: Sokoban, the Rubik’s Cube, and the inequality-proving benchmark INT.