{"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/studying-the-interplay-between-the-actor-and","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","arxiv_id":"2503.06343","date":"2025-03-08","proceeding":null,"authors":["Samuel Garcin","Trevor McInroe","Pablo Samuel Castro","Prakash Panangaden","Christopher G. Lucas","David Abel","Stefano V. Albrecht"],"abstract":"Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and the critic. To this end, we here explore the principles that underlie effective representations for the actor and for the critic in on-policy algorithms. We focus our study on understanding whether the actor and critic will benefit from separate, rather than shared, representations. Our primary finding is that when separated, the representations for the actor and critic systematically specialise in extracting different types of information from the environment -- the actor's representation tends to focus on action-relevant information, while the critic's representation specialises in encoding value and dynamics information. We conduct a rigourous empirical study to understand how different representation learning approaches affect the actor and critic's specialisations and their downstream performance, in terms of sample efficiency and generation capabilities. Finally, we discover that a separated critic plays an important role in exploration and data collection during training. Our code, trained models and data are accessible at https://github.com/francelico/deac-rep.","url_abs":"https://arxiv.org/abs/2503.06343v2","url_pdf":"https://arxiv.org/pdf/2503.06343v2.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":"studying-the-interplay-between-the-actor-and","repo_url":"https://github.com/francelico/deac-rep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06343"}},"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":"deterministic:regex_extraction","url":"https://github.com/francelico/deac-rep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"2e836db324c441d5","entry":"flatten","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/eval_utils/mutual_info_procgen_eval.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/eval_utils/mutual_info_procgen_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e836db324c441d5"}},{"code_sha256_prefix":"48466eb97d63e6ed","entry":"layer_init_normed_make_fn","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/utils/model_util.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/utils/model_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48466eb97d63e6ed"}},{"code_sha256_prefix":"44563d039e270c59","entry":"make_opt","repo":"francelico/deac-rep","repo_kind":"official","path":"brax_experiments/train_scripts/train_dcpg.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/brax_experiments/train_scripts/train_dcpg.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44563d039e270c59"}},{"code_sha256_prefix":"b81e0663664c16d2","entry":"prepare_data","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/eval_utils/mutual_info_procgen_eval.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/eval_utils/mutual_info_procgen_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b81e0663664c16d2"}},{"code_sha256_prefix":"cd4d33a05a1fc39c","entry":"random_projection","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/utils/model_util.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/utils/model_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd4d33a05a1fc39c"}},{"code_sha256_prefix":"8a9250b415d9f888","entry":"set_layer_init_fn","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/utils/model_util.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/utils/model_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a9250b415d9f888"}},{"code_sha256_prefix":"f73e23e506f33203","entry":"step_envs_once","repo":"francelico/deac-rep","repo_kind":"official","path":"procgen_experiments/eval_utils/mutual_info_procgen_eval.py","file_url":"https://github.com/francelico/deac-rep/blob/HEAD/procgen_experiments/eval_utils/mutual_info_procgen_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f73e23e506f33203"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}