{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","arxiv_id":"2104.09122","date":"2021-04-19","proceeding":null,"authors":["Jie Ren","Yewen Li","Zihan Ding","Wei Pan","Hao Dong"],"abstract":"Deep reinforcement learning (DRL) has successfully solved various problems recently, typically with a unimodal policy representation. However, grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance, which may lead to a multimodal policy represented as a mixture-of-experts (MOE). To our best knowledge, present DRL algorithms for general utility do not deploy this method as policy function approximators due to the potential challenge in its differentiability for policy learning. In this work, we propose a probabilistic mixture-of-experts (PMOE) implemented with a Gaussian mixture model (GMM) for multimodal policy, together with a novel gradient estimator for the indifferentiability problem, which can be applied in generic off-policy and on-policy DRL algorithms using stochastic policies, e.g., Soft Actor-Critic (SAC) and Proximal Policy Optimisation (PPO). Experimental results testify the advantage of our method over unimodal polices and two different MOE methods, as well as a method of option frameworks, based on the above two types of DRL algorithms, on six MuJoCo tasks. Different gradient estimations for GMM like the reparameterisation trick (Gumbel-Softmax) and the score-ratio trick are also compared with our method. We further empirically demonstrate the distinguishable primitives learned with PMOE and show the benefits of our method in terms of exploration.","url_abs":"https://arxiv.org/abs/2104.09122v1","url_pdf":"https://arxiv.org/pdf/2104.09122v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"probabilistic-mixture-of-experts-for-1","repo_url":"https://github.com/JieRen98/rlkit-pmoe","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09122"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JieRen98/rlkit-pmoe","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_honours":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"93d28ca67303e04b","entry":"clip_magnitude","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/pythonplusplus.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93d28ca67303e04b"}},{"code_sha256_prefix":"fadf5f762ff04cd6","entry":"create_stats_ordered_dict","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/core/eval_util.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/core/eval_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fadf5f762ff04cd6"}},{"code_sha256_prefix":"a5d10a0b704c8db7","entry":"get_average_returns","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/core/eval_util.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/core/eval_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5d10a0b704c8db7"}},{"code_sha256_prefix":"9910e2fc297f8665","entry":"identity","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/pythonplusplus.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9910e2fc297f8665"}},{"code_sha256_prefix":"4138766e854db009","entry":"is_numeric","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/pythonplusplus.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/pythonplusplus.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4138766e854db009"}},{"code_sha256_prefix":"5cb0c55f58279f59","entry":"simple_separated_format","repo":"JieRen98/rlkit-pmoe","repo_kind":"official","path":"rlkit/core/tabulate.py","file_url":"https://github.com/JieRen98/rlkit-pmoe/blob/HEAD/rlkit/core/tabulate.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cb0c55f58279f59"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}