Learning to Plan via Deep Optimistic Value Exploration
Deep exploration requires coordinated long-term planning. We present a model-based reinforcement learning algorithm that guides policy learning through a value function that exhibits optimism in the face of uncertainty. We capture uncertainty over values by combining predictions from an ensemble of models and formulate an upper confidence bound (UCB) objective to recover optimistic estimates. Training the policy on ensemble rollouts with the learned value function as the terminal cost allows for projecting long-term interactions into a limited planning horizon, thus enabling deep optimistic exploration. We do not assume a priori knowledge of either the dynamics or reward function. We demonstrate that our approach can accommodate both dense and sparse reward signals, while improving sample complexity on a variety of benchmarking tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingModel-based Reinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Learning to Plan Optimistically: Uncertainty-Guided Deep Exploration via Latent Model Ensembles
Learning complex robot behaviors through interaction requires structured exploration. Planning should target interactions with the potential to optimize long-term performance, while only reducing uncertainty where conduc…
Decision MakingOptimistic Exploration even with a Pessimistic Initialisation
Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algor…
Efficient ExplorationQ-LearningReinforcement LearningReinforcement Learning (RL)DOP: Deep Optimistic Planning with Approximate Value Function Evaluation
Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high unc…
Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Randomized Exploration for Reinforcement Learning with General Value Function Approximation
We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning
The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, due to the representational limitations of traditional monotonic value deco…
Multi-agent Reinforcement Learning