Transfer of Reinforcement Learning Negotiation Policies: From Bilateral to Multilateral Scenarios.
Ioannis EfstathiouOliver LemonPublished in: ECAI (2016)
Keyphrases
- negotiation support systems
- reinforcement learning
- optimal policy
- transfer learning
- policy search
- markov decision process
- control policies
- function approximation
- reinforcement learning agents
- markov decision processes
- reinforcement learning algorithms
- control policy
- management policies
- hierarchical reinforcement learning
- learning algorithm
- model free
- real world
- partially observable markov decision processes
- fitted q iteration
- reward function
- decision problems
- knowledge transfer
- machine learning
- dynamic programming
- temporal difference
- markov decision problems
- continuous state
- multiagent reinforcement learning
- action space
- learning process
- multi agent
- policy gradient methods
- reinforcement learning methods
- state abstraction
- long run
- multi issue
- state space