Search Results for author:
Found 25 papers, 11 papers with code
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems.
MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning
To this end, based on the characteristics of embodied task planning, we first develop a systematic evaluation framework, which encapsulates four crucial capabilities of MFMs: object understanding, spatio-temporal perception, task understanding, and embodied reasoning.
Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms
Evolutionary Reinforcement Learning (ERL), which integrates Evolutionary Algorithms (EAs) and Reinforcement Learning (RL) for optimization, has demonstrated remarkable performance advancements.
The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting
On typical MuJoCo and DeepMind Control Suite (DMC) benchmarks, we find common phenomena for TD3 and RAD agents: 1) the activity of policy network parameters is highly asymmetric and policy networks advance monotonically along very few major parameter directions; 2) severe detours occur in parameter update and harmonic-like changes are observed for all minor parameter directions.
State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning
The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way.
ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
The state representation conveys expressive common features of the environment learned by all the agents collectively; the linear policy representation provides a favorable space for efficient policy optimization, where novel behavior-level crossover and mutation operations can be performed.
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes
First, we propose a unified policy abstraction theory, containing three types of policy abstraction associated to policy features at different levels.
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF.
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning
Such a reconstruction exploits the underlying structure of value matrix to improve the value approximation, thus leading to a more efficient learning process of value function.
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
In addition to algorithmic analysis, we provide a comprehensive and unified empirical comparison of different exploration methods for DRL on a set of commonly used benchmarks.
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI.
Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction
Value function is the central notion of Reinforcement Learning (RL).
Addressing Action Oscillations through Learning Policy Inertia
We propose Nested Policy Iteration as a general training algorithm for PIC-augmented policy which ensures monotonically non-decreasing updates under some mild conditions.
What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator
We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation.
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
How to collect informative trajectories of which the corresponding context reflects the specification of tasks?
Transfer among Agents: An Efficient Multiagent Transfer Learning Framework
In many cases, each agent's experience is inconsistent with each other which causes the option-value estimation to oscillate and to become inaccurate.
Open-Ended Question Answering
Reinforcement Learning (RL)
+1
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state.
KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
Our framework consists of a fuzzy rule controller to represent human knowledge and a refine module to fine-tune suboptimal prior knowledge.
MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space.
Efficient meta reinforcement learning via meta goal generation
Meta reinforcement learning (meta-RL) is able to accelerate the acquisition of new tasks by learning from past experience.
Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates.
Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces
Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+3
Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction
Besides, we propose a new experience replay mechanism to alleviate the issue of the sparse transitions at the high level of abstraction and the non-stationarity of multiagent learning.
An Optimal Rewiring Strategy for Reinforcement Social Learning in Cooperative Multiagent Systems
Multiagent coordination in cooperative multiagent systems (MASs) has been widely studied in both fixed-agent repeated interaction setting and the static social learning framework.
