Anthony GX-Chen

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

Mandana Samiei, Eunice Yiu, Anthony GX-Chen, Dexin Lin et autres

A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on …

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

Mandana Samiei, Eunice Yiu, Anthony GX-Chen, Dexin Lin et autres

A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on …

us, ca (code pays fourni par la source)

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Anthony GX-Chen, Ankit Anand, Gheorghe Comanici, Zaheer Abbas et autres

Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require …

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Anthony GX-Chen, Ankit Anand, Gheorghe Comanici, Dr. Zaheer Abbas et autres

Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require …

us (code pays fourni par la source)

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models

AD Jhaveri, Anthony GX-Chen, Ilia Sucholutsky, Eunsol Choi

Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery study from human psychology: given a sequence of three numbers …

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models

AD Jhaveri, Anthony GX-Chen, Ilia Sucholutsky, Eunsol Choi

Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery study from human psychology: given a sequence of three numbers …

Sample-efficient generative molecular design using memory manipulation

Jeff Guo, Junwu Chen, Anthony GX-Chen, Philippe Schwaller

ch, us (code pays fourni par la source)

KL-Regularized Reinforcement Learning is Designed to Mode Collapse

Anthony GX-Chen, Jatin Prakash, Jeff Guo, Rob Fergus et autres

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We show -- mathematically and …

Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?

Anthony GX-Chen, Dongyan Lin, Mandana Samiei, Doina Precup et autres

Language model (LM) agents are increasingly used as autonomous decision-makers which need to actively gather information to guide their decisions. A crucial cognitive skill for such agents is the efficient exploration and understanding of the causal structure of the world -- key …

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen, Kenneth Marino, Rob Fergus

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is best solved hierarchically by modelling …

Light-weight probing of unsupervised representations for Reinforcement Learning

Wancong Zhang, Anthony GX-Chen, Vlad Sobal, Yann LeCun et autres

Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms. However, evaluating the fitness of such representations requires training RL algorithms which is …

A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions

Anthony GX-Chen, Veronica Chelu, Blake Richards, Joëlle Pineau

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value function toward a learning target using value estimates at subsequent time-steps. Alternatively, the value function can be updated toward …

ca (code pays fourni par la source)