Search papers and tags

Catalog Tags

Tag Explorer All

formal-methods 24 reinforcement-learning 17 safe-rl 17 temporal-logic 14 multi-agent-rl 12 shielding 9 model-checking 7 multi-agent-systems 7 linear-temporal-logic 6 causal-modeling 5 game-theory 5 strategic-reasoning 5 value-alignment 5 ai-safety 4 cooperation 4 deep-rl 4 reactive-systems 4 survey 4 cooperative-marl 3 ethical-ai 3 nash-equilibrium 3 probabilistic-safety 3 task-decomposition 3 automata-theory 2 compositional-verification 2 constrained-markov-games 2 constrained-mdps 2 constrained-policy-optimization 2 coordination 2 counterfactual-reasoning 2 dynamic-programming 2 modal-logic 2 policy-optimization 2 q-learning 2 reasoning-about-actions 2 sample-complexity 2 temporal-difference-learning 2 action-masking 1 aspiration-based-learning 1 assume-guarantee-reasoning 1 behavioral-game-theory 1 bounded-rationality 1 computational-complexity 1 computer-aided-verification 1 controlled-invariant-sets 1 corrigibility 1 data-driven-control 1 deception 1 decision-making 1 decision-trees 1 dyadic-morality 1 emergent-communication 1 evolutionary-game-theory 1 explainable-ai 1 game-semantics 1 hamilton-jacobi-reachability 1 linear-mdps 1 markov-decision-processes 1 markov-potential-games 1 mean-field-rl 1 mixed-motive-games 1 model-based-rl 1 model-free-rl 1 moral-reasoning 1 neurosymbolic-ai 1 non-markovian-rewards 1 non-stationarity 1 off-policy-rl 1 off-switch-game 1 on-policy-rl 1 open-multi-agent-systems 1 partial-observability 1 ppo 1 probabilistic-model-checking 1 program-semantics 1 repeated-games 1 responsibility-attribution 1 reward-machines 1 reward-shaping 1 robotics 1 runtime-enforcement 1 signaling-games 1 social-learning 1 stochastic-games 1 symbolic-verification 1 transition-systems 1 value-decomposition 1

2022

Multi-Agent Constrained Policy Optimisation

constrained-markov-games constrained-policy-optimization multi-agent-rl policy-optimization safe-rl

Paper page PDF

Year: 2022
Authors: Anonymous Submission
arXiv: 2110.02793 [cs.AI]

Abstract

1.

Generated from paper-tags.json.