Search Results for author:
Found 17 papers, 10 papers with code
Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards
During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward.
Mixture of Attentions For Speculative Decoding
The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy.
ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback.
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies.
Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning
This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained with a Language Modelling (LM) objective.
End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
Sample-Efficient Optimisation with Probabilistic Transformer Surrogates
First, we notice that these models are trained on uniformly distributed inputs, which impairs predictive accuracy on non-uniform data - a setting arising from any typical BO loop due to exploration-exploitation trade-offs.
Neuro-Symbolic Hierarchical Rule Induction
We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems.
A Survey on Interpretable Reinforcement Learning
To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion.
Differentiable Logic Machines
As a step in this direction, we propose a novel neural-logic architecture, called differentiable logic machine (DLM), that can solve both inductive logic programming (ILP) and reinforcement learning (RL) problems, where the solution can be interpreted as a first-order logic program.
Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness.
Hyperparameter Auto-tuning in Self-Supervised Robotic Learning
Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources.
Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards
Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward.
Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation
Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements.
Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning
Our work demonstrates that invariant transformations on RL trajectories are a promising methodology to speed up learning in deep RL.
Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains
In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC).
