A multi-agent off-policy actor-critic algorithm for distributed reinforcement learning

Keyphrases

• Multi-agent 100%
• Distributed Reinforcement Learning 100%
• Actor-critic Algorithm 100%
• Policy Actors 100%
• Convergence Guarantee 16%
• Networked Agents 16%
• Time-varying Graphs 16%
• Linear Function Approximation 16%
• Behavioral Policy 16%
• Policy Learning 16%
• Actor-critic Methods 16%
• Temporal Difference Learning 16%
• Off-policy Evaluation 16%
• On-policy 16%
• Policy Gradient Theorem 16%

Computer Science

• multi agent 100%
• Reinforcement Learning 100%
• Function Approximation 16%
• temporal difference learning 16%
• Linear Function 16%